DreamFast's picture
Upload folder using huggingface_hub
93b7c55 verified
Raw
History Blame Contribute Delete
283 kB
{
"base_model": "Qwen3.6-35B-A3B",
"converted_model": "Qwen3.6-35B-A3B-HauhauCS-Q8KP-recovered",
"summary": {
"total_tensors": 1045,
"gguf_derived": 693,
"copied": 352,
"gguf_identical": 307,
"gguf_modified": 386,
"copied_identical": 352,
"copied_modified": 0
},
"tensors": [
{
"group": "lm_head",
"name": "lm_head.weight",
"max_abs_diff": 0.0010833740234375,
"mean_abs_diff": 8.252273983089253e-05,
"pct_different": 75.062035236162,
"n_different": 381735006,
"total_elements": 508559360
},
{
"group": "embed_tokens",
"name": "model.language_model.embed_tokens.weight",
"max_abs_diff": 0.0011444091796875,
"mean_abs_diff": 5.407223216025159e-05,
"pct_different": 74.34011262716706,
"n_different": 378063601,
"total_elements": 508559360
},
{
"group": "layernorm",
"name": "model.language_model.layers.0.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.0.linear_attn.A_log",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.0.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.0.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.0.linear_attn.in_proj_a.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 1.4910934709178036e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.0.linear_attn.in_proj_b.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 1.2775558388966601e-11,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 8.525864042541187e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.0.linear_attn.in_proj_z.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 5.649228480841817e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.0.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.0.linear_attn.out_proj.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 6.961986218811944e-05,
"pct_different": 75.75498819351196,
"n_different": 6354789,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.0.mlp.experts.down_proj",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 2.2513979274663143e-05,
"pct_different": 41.840748116374016,
"n_different": 112315403,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.0.mlp.experts.gate_up_proj",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 2.283455069118645e-05,
"pct_different": 43.73089522123337,
"n_different": 234778456,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.0.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.0.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 5.048537423135713e-05,
"pct_different": 76.28936767578125,
"n_different": 799952,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.0.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 5.523828076547943e-05,
"pct_different": 75.71783065795898,
"n_different": 793959,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.0.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.000518798828125,
"mean_abs_diff": 4.961384547641501e-05,
"pct_different": 75.92239379882812,
"n_different": 796104,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.0.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.0.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.1.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.1.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 5.587935447692871e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.1.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.1.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.1.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 0.00010247129830531776,
"pct_different": 75.79345703125,
"n_different": 49672,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.1.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 7.084233220666647e-05,
"pct_different": 76.63116455078125,
"n_different": 50221,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.0010986328125,
"mean_abs_diff": 7.131708116503432e-05,
"pct_different": 73.38083386421204,
"n_different": 12311261,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.1.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001129150390625,
"mean_abs_diff": 7.232930511236191e-05,
"pct_different": 75.3028392791748,
"n_different": 6316860,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.1.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.1.linear_attn.out_proj.weight",
"max_abs_diff": 0.00244140625,
"mean_abs_diff": 6.931642565177754e-05,
"pct_different": 75.44991970062256,
"n_different": 6329198,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.1.mlp.experts.down_proj",
"max_abs_diff": 0.00067138671875,
"mean_abs_diff": 4.346974310465157e-05,
"pct_different": 72.96010702848434,
"n_different": 195850796,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.1.mlp.experts.gate_up_proj",
"max_abs_diff": 0.00048828125,
"mean_abs_diff": 4.111788803129457e-05,
"pct_different": 73.11219181865454,
"n_different": 392518091,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.1.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.1.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.00152587890625,
"mean_abs_diff": 5.1677961891982704e-05,
"pct_different": 76.61848068237305,
"n_different": 803403,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.1.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0006256103515625,
"mean_abs_diff": 5.2743715059477836e-05,
"pct_different": 76.08728408813477,
"n_different": 797833,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.1.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00067138671875,
"mean_abs_diff": 5.0087764975614846e-05,
"pct_different": 75.72908401489258,
"n_different": 794077,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.1.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.1.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.10.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.10.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 6.984919309616089e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.10.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.10.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.10.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.00091552734375,
"mean_abs_diff": 8.147383050527424e-05,
"pct_different": 77.166748046875,
"n_different": 50572,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.10.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 6.659454084001482e-05,
"pct_different": 77.89306640625,
"n_different": 51048,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 7.837942393962294e-05,
"pct_different": 76.2194037437439,
"n_different": 12787494,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.10.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.00115966796875,
"mean_abs_diff": 6.460334407165647e-05,
"pct_different": 75.69509744644165,
"n_different": 6349765,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.10.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.10.linear_attn.out_proj.weight",
"max_abs_diff": 0.0032501220703125,
"mean_abs_diff": 6.71583111397922e-05,
"pct_different": 75.81313848495483,
"n_different": 6359667,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.10.mlp.experts.down_proj",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.468904808163643e-05,
"pct_different": 74.31734949350357,
"n_different": 199494116,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.10.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.599253225023858e-05,
"pct_different": 74.45449084043503,
"n_different": 399724504,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.10.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.10.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 4.9545975343789905e-05,
"pct_different": 77.01168060302734,
"n_different": 807526,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.10.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 4.3953972635790706e-05,
"pct_different": 77.45733261108398,
"n_different": 812199,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.10.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00109100341796875,
"mean_abs_diff": 5.314434747560881e-05,
"pct_different": 77.25858688354492,
"n_different": 810115,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.10.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.10.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.11.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.11.mlp.experts.down_proj",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.479318158701062e-05,
"pct_different": 74.24698136746883,
"n_different": 199305223,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.11.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.596764483721927e-05,
"pct_different": 74.33178629726171,
"n_different": 399065739,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.11.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.11.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 4.926586916553788e-05,
"pct_different": 76.67951583862305,
"n_different": 804043,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.11.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 4.042325235786848e-05,
"pct_different": 76.7068862915039,
"n_different": 804330,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.11.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 5.266155494609848e-05,
"pct_different": 77.04896926879883,
"n_different": 807917,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.11.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.11.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.11.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.11.self_attn.k_proj.weight",
"max_abs_diff": 0.000823974609375,
"mean_abs_diff": 7.404887583106756e-05,
"pct_different": 76.78871154785156,
"n_different": 805188,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.11.self_attn.o_proj.weight",
"max_abs_diff": 0.0023193359375,
"mean_abs_diff": 6.212470907485113e-05,
"pct_different": 75.56613683700562,
"n_different": 6338947,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.11.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.11.self_attn.q_proj.weight",
"max_abs_diff": 0.00098419189453125,
"mean_abs_diff": 7.024329534033313e-05,
"pct_different": 75.72547793388367,
"n_different": 12704627,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.11.self_attn.v_proj.weight",
"max_abs_diff": 0.00067138671875,
"mean_abs_diff": 6.010285869706422e-05,
"pct_different": 77.16293334960938,
"n_different": 809112,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.12.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.12.linear_attn.A_log",
"max_abs_diff": 2.60770320892334e-08,
"mean_abs_diff": 2.0372681319713593e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.12.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.12.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.12.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 8.491073094774038e-05,
"pct_different": 77.5177001953125,
"n_different": 50802,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.12.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00067138671875,
"mean_abs_diff": 6.888517236802727e-05,
"pct_different": 78.94287109375,
"n_different": 51736,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.0010986328125,
"mean_abs_diff": 7.734443352092057e-05,
"pct_different": 76.01020932197571,
"n_different": 12752397,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.12.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 6.149078399175778e-05,
"pct_different": 75.670325756073,
"n_different": 6347687,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.12.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.12.linear_attn.out_proj.weight",
"max_abs_diff": 0.0029296875,
"mean_abs_diff": 6.728764128638431e-05,
"pct_different": 75.66553354263306,
"n_different": 6347285,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.12.mlp.experts.down_proj",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.417969466885552e-05,
"pct_different": 74.31587390601635,
"n_different": 199490155,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.12.mlp.experts.gate_up_proj",
"max_abs_diff": 0.000823974609375,
"mean_abs_diff": 4.582593828672543e-05,
"pct_different": 74.47806298732758,
"n_different": 399851056,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.12.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.12.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 4.871177225140855e-05,
"pct_different": 76.48048400878906,
"n_different": 801956,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.12.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0006866455078125,
"mean_abs_diff": 4.3372703657951206e-05,
"pct_different": 76.93452835083008,
"n_different": 806717,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.12.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0008544921875,
"mean_abs_diff": 5.3502088121604174e-05,
"pct_different": 76.98135375976562,
"n_different": 807208,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.12.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.12.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.13.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.13.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 3.725290298461914e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.13.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.13.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.13.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 8.881848771125078e-05,
"pct_different": 77.23846435546875,
"n_different": 50619,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.13.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 7.101592927938327e-05,
"pct_different": 78.8909912109375,
"n_different": 51702,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001708984375,
"mean_abs_diff": 7.823992928024381e-05,
"pct_different": 75.72848200798035,
"n_different": 12705131,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.13.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.0013427734375,
"mean_abs_diff": 6.614800804527476e-05,
"pct_different": 75.77245235443115,
"n_different": 6356254,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.13.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.13.linear_attn.out_proj.weight",
"max_abs_diff": 0.0029296875,
"mean_abs_diff": 6.55348485452123e-05,
"pct_different": 75.51208734512329,
"n_different": 6334413,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.13.mlp.experts.down_proj",
"max_abs_diff": 0.0521240234375,
"mean_abs_diff": 0.00016416661674156785,
"pct_different": 84.88881774246693,
"n_different": 227871685,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.13.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.592622281052172e-05,
"pct_different": 74.48321487754583,
"n_different": 399878715,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.13.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.13.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.013936042785644531,
"mean_abs_diff": 0.00018142559565603733,
"pct_different": 86.73515319824219,
"n_different": 909484,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.13.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.01434326171875,
"mean_abs_diff": 0.0002482789568603039,
"pct_different": 91.60451889038086,
"n_different": 960543,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.13.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.017669677734375,
"mean_abs_diff": 0.000301205349387601,
"pct_different": 91.26052856445312,
"n_different": 956936,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.13.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.13.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.14.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.14.linear_attn.A_log",
"max_abs_diff": 4.470348358154297e-08,
"mean_abs_diff": 6.05359673500061e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.14.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.14.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.14.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.00067138671875,
"mean_abs_diff": 9.136922017205507e-05,
"pct_different": 76.93939208984375,
"n_different": 50423,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.14.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 7.59142785682343e-05,
"pct_different": 79.17022705078125,
"n_different": 51885,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 8.208391955122352e-05,
"pct_different": 76.49259567260742,
"n_different": 12833328,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.14.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.00128173828125,
"mean_abs_diff": 5.960601265542209e-05,
"pct_different": 75.62425136566162,
"n_different": 6343822,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.14.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.14.linear_attn.out_proj.weight",
"max_abs_diff": 0.0029296875,
"mean_abs_diff": 6.70628432999365e-05,
"pct_different": 75.70273876190186,
"n_different": 6350406,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.14.mlp.experts.down_proj",
"max_abs_diff": 0.04425048828125,
"mean_abs_diff": 0.00016297487309202552,
"pct_different": 84.52954217791557,
"n_different": 226907262,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.14.mlp.experts.gate_up_proj",
"max_abs_diff": 0.000823974609375,
"mean_abs_diff": 4.612559496308677e-05,
"pct_different": 74.47763811796904,
"n_different": 399848775,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.14.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.14.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0081787109375,
"mean_abs_diff": 0.0001611674961168319,
"pct_different": 85.93358993530273,
"n_different": 901079,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.14.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.021148681640625,
"mean_abs_diff": 0.00024421149282716215,
"pct_different": 92.06600189208984,
"n_different": 965382,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.14.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.020172119140625,
"mean_abs_diff": 0.000316268065944314,
"pct_different": 92.00611114501953,
"n_different": 964754,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.14.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.14.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.15.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.15.mlp.experts.down_proj",
"max_abs_diff": 0.0494384765625,
"mean_abs_diff": 0.0001675536041148007,
"pct_different": 84.93725061416626,
"n_different": 228001696,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.15.mlp.experts.gate_up_proj",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 4.624357825377956e-05,
"pct_different": 74.51016400009394,
"n_different": 400023397,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.15.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.15.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0068206787109375,
"mean_abs_diff": 0.00018666769028641284,
"pct_different": 85.87207794189453,
"n_different": 900434,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.15.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.014892578125,
"mean_abs_diff": 0.0002611585659906268,
"pct_different": 92.0541763305664,
"n_different": 965258,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.15.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.017822265625,
"mean_abs_diff": 0.0003065799246542156,
"pct_different": 91.16964340209961,
"n_different": 955983,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.15.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.15.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.15.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.15.self_attn.k_proj.weight",
"max_abs_diff": 0.000762939453125,
"mean_abs_diff": 7.148747681640089e-05,
"pct_different": 75.90646743774414,
"n_different": 795937,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.15.self_attn.o_proj.weight",
"max_abs_diff": 0.0203857421875,
"mean_abs_diff": 0.00028440827736631036,
"pct_different": 86.1541748046875,
"n_different": 7227136,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.15.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.15.self_attn.q_proj.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 6.535403372254223e-05,
"pct_different": 75.44593811035156,
"n_different": 12657728,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.15.self_attn.v_proj.weight",
"max_abs_diff": 0.0008392333984375,
"mean_abs_diff": 6.21751241851598e-05,
"pct_different": 76.96361541748047,
"n_different": 807022,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.16.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.16.linear_attn.A_log",
"max_abs_diff": 2.60770320892334e-08,
"mean_abs_diff": 1.7462298274040222e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.16.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.16.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.16.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 8.392307790927589e-05,
"pct_different": 77.79388427734375,
"n_different": 50983,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.16.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00048828125,
"mean_abs_diff": 7.065702811814845e-05,
"pct_different": 79.93927001953125,
"n_different": 52389,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.00152587890625,
"mean_abs_diff": 7.918636401882395e-05,
"pct_different": 76.08726024627686,
"n_different": 12765324,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.16.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.000946044921875,
"mean_abs_diff": 6.070804738556035e-05,
"pct_different": 75.6017804145813,
"n_different": 6341937,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.16.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.16.linear_attn.out_proj.weight",
"max_abs_diff": 0.0313262939453125,
"mean_abs_diff": 0.00042332825250923634,
"pct_different": 87.5267505645752,
"n_different": 7342276,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.16.mlp.experts.down_proj",
"max_abs_diff": 0.0648193359375,
"mean_abs_diff": 0.00016193953342735767,
"pct_different": 84.56891477108002,
"n_different": 227012952,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.16.mlp.experts.gate_up_proj",
"max_abs_diff": 0.00091552734375,
"mean_abs_diff": 4.633928620023653e-05,
"pct_different": 74.55773949623108,
"n_different": 400278816,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.16.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.16.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0152587890625,
"mean_abs_diff": 0.0001946525153471157,
"pct_different": 85.45475006103516,
"n_different": 896058,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.16.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0164794921875,
"mean_abs_diff": 0.00023676974524278194,
"pct_different": 91.48035049438477,
"n_different": 959241,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.16.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.020782470703125,
"mean_abs_diff": 0.0003119264729321003,
"pct_different": 91.4423942565918,
"n_different": 958843,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.16.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.16.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.17.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.17.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 6.28642737865448e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.17.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.17.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.17.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 8.629968215245754e-05,
"pct_different": 77.74810791015625,
"n_different": 50953,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.17.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.0006256103515625,
"mean_abs_diff": 7.553433533757925e-05,
"pct_different": 79.681396484375,
"n_different": 52220,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 7.878502947278321e-05,
"pct_different": 76.20041966438293,
"n_different": 12784309,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.17.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.00115966796875,
"mean_abs_diff": 6.115087307989597e-05,
"pct_different": 75.67152976989746,
"n_different": 6347788,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.17.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.17.linear_attn.out_proj.weight",
"max_abs_diff": 0.0562744140625,
"mean_abs_diff": 0.0004396997392177582,
"pct_different": 88.25094699859619,
"n_different": 7403026,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.17.mlp.experts.down_proj",
"max_abs_diff": 0.03216552734375,
"mean_abs_diff": 0.00015920473379082978,
"pct_different": 84.28642712533474,
"n_different": 226254655,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.17.mlp.experts.gate_up_proj",
"max_abs_diff": 0.00116729736328125,
"mean_abs_diff": 4.64716213173233e-05,
"pct_different": 74.56007972359657,
"n_different": 400291380,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.17.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.17.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.011739730834960938,
"mean_abs_diff": 0.00018112431280314922,
"pct_different": 86.3363265991211,
"n_different": 905302,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.17.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.016632080078125,
"mean_abs_diff": 0.0002529557386878878,
"pct_different": 92.07258224487305,
"n_different": 965451,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.17.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0181884765625,
"mean_abs_diff": 0.00030651784618385136,
"pct_different": 91.57915115356445,
"n_different": 960277,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.17.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.17.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.18.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.18.linear_attn.A_log",
"max_abs_diff": 5.21540641784668e-08,
"mean_abs_diff": 8.614733815193176e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.18.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.18.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.18.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.0005645751953125,
"mean_abs_diff": 7.99209374235943e-05,
"pct_different": 77.197265625,
"n_different": 50592,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.18.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00048828125,
"mean_abs_diff": 7.153955812100321e-05,
"pct_different": 79.58526611328125,
"n_different": 52157,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.0013427734375,
"mean_abs_diff": 8.00086636445485e-05,
"pct_different": 76.21898055076599,
"n_different": 12787423,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.18.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.0012054443359375,
"mean_abs_diff": 6.136030424386263e-05,
"pct_different": 75.68267583847046,
"n_different": 6348723,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.18.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.18.linear_attn.out_proj.weight",
"max_abs_diff": 0.0517578125,
"mean_abs_diff": 0.00043412059312686324,
"pct_different": 87.82045841217041,
"n_different": 7366914,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.18.mlp.experts.down_proj",
"max_abs_diff": 0.039794921875,
"mean_abs_diff": 0.00016504473751410842,
"pct_different": 84.63703133165836,
"n_different": 227195801,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.18.mlp.experts.gate_up_proj",
"max_abs_diff": 0.00347900390625,
"mean_abs_diff": 5.337321636034176e-05,
"pct_different": 75.7801840081811,
"n_different": 406841765,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.18.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.18.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0206451416015625,
"mean_abs_diff": 0.00019821515888907015,
"pct_different": 86.01350784301758,
"n_different": 901917,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.18.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.01983642578125,
"mean_abs_diff": 0.00026794103905558586,
"pct_different": 91.8386459350586,
"n_different": 962998,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.18.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0192413330078125,
"mean_abs_diff": 0.00031468673842027783,
"pct_different": 91.53776168823242,
"n_different": 959843,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.18.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.18.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.19.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.19.mlp.experts.down_proj",
"max_abs_diff": 0.05120849609375,
"mean_abs_diff": 0.00015744150732643902,
"pct_different": 84.36407223343849,
"n_different": 226463082,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.19.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0045166015625,
"mean_abs_diff": 5.5417978728655726e-05,
"pct_different": 76.07477195560932,
"n_different": 408423322,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.19.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.19.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0142364501953125,
"mean_abs_diff": 0.00020512893388513476,
"pct_different": 85.77165603637695,
"n_different": 899381,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.19.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.019378662109375,
"mean_abs_diff": 0.00027195975417271256,
"pct_different": 91.9621467590332,
"n_different": 964293,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.19.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0177459716796875,
"mean_abs_diff": 0.00028497763560153544,
"pct_different": 90.75374603271484,
"n_different": 951622,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.19.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.19.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.19.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.19.self_attn.k_proj.weight",
"max_abs_diff": 0.0008544921875,
"mean_abs_diff": 6.671935261692852e-05,
"pct_different": 75.68769454956055,
"n_different": 793643,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.19.self_attn.o_proj.weight",
"max_abs_diff": 0.013702392578125,
"mean_abs_diff": 0.00032492561149410903,
"pct_different": 86.81050539016724,
"n_different": 7282193,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.19.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.19.self_attn.q_proj.weight",
"max_abs_diff": 0.00152587890625,
"mean_abs_diff": 6.43174716969952e-05,
"pct_different": 75.52264928817749,
"n_different": 12670598,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.19.self_attn.v_proj.weight",
"max_abs_diff": 0.000885009765625,
"mean_abs_diff": 5.9716574469348416e-05,
"pct_different": 76.54294967651367,
"n_different": 802611,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.2.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.2.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 8.934875950217247e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.2.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.2.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.2.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 8.202709432225674e-05,
"pct_different": 76.78375244140625,
"n_different": 50321,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.2.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 6.774281791877002e-05,
"pct_different": 77.33917236328125,
"n_different": 50685,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.0010223388671875,
"mean_abs_diff": 7.253498188219965e-05,
"pct_different": 74.60963129997253,
"n_different": 12517419,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.2.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 6.867479532957077e-05,
"pct_different": 75.54035186767578,
"n_different": 6336784,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.2.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.2.linear_attn.out_proj.weight",
"max_abs_diff": 0.0025634765625,
"mean_abs_diff": 6.926805508555844e-05,
"pct_different": 75.59624910354614,
"n_different": 6341473,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.2.mlp.experts.down_proj",
"max_abs_diff": 0.0010986328125,
"mean_abs_diff": 4.4208281906321645e-05,
"pct_different": 73.6159261316061,
"n_different": 197611247,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.2.mlp.experts.gate_up_proj",
"max_abs_diff": 0.00048828125,
"mean_abs_diff": 4.319091749493964e-05,
"pct_different": 73.7625615671277,
"n_different": 396009737,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.2.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.2.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 5.134729508426972e-05,
"pct_different": 76.46913528442383,
"n_different": 801837,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.2.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0008544921875,
"mean_abs_diff": 5.1316088502062485e-05,
"pct_different": 76.29518508911133,
"n_different": 800013,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.2.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 5.095137021271512e-05,
"pct_different": 76.12409591674805,
"n_different": 798219,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.2.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.2.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.20.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.20.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 1.0244548320770264e-08,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.20.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.20.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.20.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.00079345703125,
"mean_abs_diff": 9.83386707957834e-05,
"pct_different": 77.65045166015625,
"n_different": 50889,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.20.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 7.693850784562528e-05,
"pct_different": 79.76837158203125,
"n_different": 52277,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 9.300987585447729e-05,
"pct_different": 76.40116214752197,
"n_different": 12817988,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.20.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 7.48467500670813e-05,
"pct_different": 76.52759552001953,
"n_different": 6419600,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.20.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.20.linear_attn.out_proj.weight",
"max_abs_diff": 0.04833984375,
"mean_abs_diff": 0.0004897484323009849,
"pct_different": 87.95448541641235,
"n_different": 7378157,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.20.mlp.experts.down_proj",
"max_abs_diff": 0.031982421875,
"mean_abs_diff": 0.00018058609566651285,
"pct_different": 85.46429947018623,
"n_different": 229416482,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.20.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0046539306640625,
"mean_abs_diff": 2.6304203856852837e-05,
"pct_different": 41.18571151047945,
"n_different": 221114105,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.20.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.20.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0076904296875,
"mean_abs_diff": 0.00015792157500982285,
"pct_different": 87.2715950012207,
"n_different": 915109,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.20.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.010009765625,
"mean_abs_diff": 0.00017769620171748102,
"pct_different": 87.44478225708008,
"n_different": 916925,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.20.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.008056640625,
"mean_abs_diff": 0.0001709601638140157,
"pct_different": 82.69004821777344,
"n_different": 867068,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.20.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.20.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.21.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.21.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 1.2994860298931599e-08,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.21.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.21.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.21.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.00067138671875,
"mean_abs_diff": 8.94919503480196e-05,
"pct_different": 77.72674560546875,
"n_different": 50939,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.21.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.000640869140625,
"mean_abs_diff": 7.325454498641193e-05,
"pct_different": 78.9642333984375,
"n_different": 51750,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001983642578125,
"mean_abs_diff": 9.073900582734495e-05,
"pct_different": 76.03468894958496,
"n_different": 12756504,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.21.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 7.163381815189496e-05,
"pct_different": 75.85808038711548,
"n_different": 6363437,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.21.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.21.linear_attn.out_proj.weight",
"max_abs_diff": 0.03887939453125,
"mean_abs_diff": 0.0004872928839176893,
"pct_different": 87.6244306564331,
"n_different": 7350470,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.21.mlp.experts.down_proj",
"max_abs_diff": 0.037109375,
"mean_abs_diff": 0.00016394685371778905,
"pct_different": 84.71211567521095,
"n_different": 227397354,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.21.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0059356689453125,
"mean_abs_diff": 6.084999768063426e-05,
"pct_different": 76.90641526132822,
"n_different": 412888173,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.21.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.21.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.010465621948242188,
"mean_abs_diff": 0.00017318414757028222,
"pct_different": 85.81399917602539,
"n_different": 899825,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.21.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.024993896484375,
"mean_abs_diff": 0.0002270845725433901,
"pct_different": 91.97778701782227,
"n_different": 964457,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.21.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.006591796875,
"mean_abs_diff": 0.00014671919052489102,
"pct_different": 86.84186935424805,
"n_different": 910603,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.21.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.21.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.22.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.22.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 8.381903171539307e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.22.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.22.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.22.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 8.763916412135586e-05,
"pct_different": 78.04412841796875,
"n_different": 51147,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.22.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 7.63551943236962e-05,
"pct_different": 78.71856689453125,
"n_different": 51589,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001312255859375,
"mean_abs_diff": 9.141962073044851e-05,
"pct_different": 76.49833559989929,
"n_different": 12834291,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.22.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001373291015625,
"mean_abs_diff": 6.859651330159977e-05,
"pct_different": 75.9783148765564,
"n_different": 6373523,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.22.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.22.linear_attn.out_proj.weight",
"max_abs_diff": 0.0604705810546875,
"mean_abs_diff": 0.00046970107359811664,
"pct_different": 88.18075656890869,
"n_different": 7397138,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.22.mlp.experts.down_proj",
"max_abs_diff": 0.03594970703125,
"mean_abs_diff": 0.00015980028547346592,
"pct_different": 84.50240306556225,
"n_different": 226834411,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.22.mlp.experts.gate_up_proj",
"max_abs_diff": 0.007293701171875,
"mean_abs_diff": 6.297700747381896e-05,
"pct_different": 77.1355478093028,
"n_different": 414118319,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.22.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.22.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.010419845581054688,
"mean_abs_diff": 0.0001603464625077322,
"pct_different": 87.72687911987305,
"n_different": 919883,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.22.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.00958251953125,
"mean_abs_diff": 0.00015206090756691992,
"pct_different": 90.13290405273438,
"n_different": 945112,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.22.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.004852294921875,
"mean_abs_diff": 9.636639879317954e-05,
"pct_different": 83.59212875366211,
"n_different": 876527,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.22.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.22.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.23.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.23.mlp.experts.down_proj",
"max_abs_diff": 0.03167724609375,
"mean_abs_diff": 0.0001644684816710651,
"pct_different": 84.74459014832973,
"n_different": 227484527,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.23.mlp.experts.gate_up_proj",
"max_abs_diff": 0.007659912109375,
"mean_abs_diff": 6.675636541331187e-05,
"pct_different": 77.55512706935406,
"n_different": 416370918,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.23.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.23.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.007598876953125,
"mean_abs_diff": 0.00017038825899362564,
"pct_different": 85.12849807739258,
"n_different": 892637,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.23.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.008148193359375,
"mean_abs_diff": 0.000185534474439919,
"pct_different": 91.17660522460938,
"n_different": 956056,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.23.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 5.3698917326983064e-05,
"pct_different": 77.85634994506836,
"n_different": 816383,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.23.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.23.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.23.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.23.self_attn.k_proj.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 8.426675776718184e-05,
"pct_different": 77.13603973388672,
"n_different": 808830,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.23.self_attn.o_proj.weight",
"max_abs_diff": 0.026458740234375,
"mean_abs_diff": 0.00031689784373156726,
"pct_different": 85.98548173904419,
"n_different": 7212985,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.23.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.23.self_attn.q_proj.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 7.806818030076101e-05,
"pct_different": 75.95778703689575,
"n_different": 12743602,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.23.self_attn.v_proj.weight",
"max_abs_diff": 0.00091552734375,
"mean_abs_diff": 6.564579962287098e-05,
"pct_different": 77.5507926940918,
"n_different": 813179,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.24.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.24.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 3.521563485264778e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.24.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.24.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.24.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 8.782851364230737e-05,
"pct_different": 78.19061279296875,
"n_different": 51243,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.24.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 7.491880387533456e-05,
"pct_different": 79.2083740234375,
"n_different": 51910,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.24.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.0013885498046875,
"mean_abs_diff": 8.98265207069926e-05,
"pct_different": 76.0124921798706,
"n_different": 12752780,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.24.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 6.668224523309618e-05,
"pct_different": 75.63703060150146,
"n_different": 6344894,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.24.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.24.linear_attn.out_proj.weight",
"max_abs_diff": 0.05377197265625,
"mean_abs_diff": 0.0004991018795408309,
"pct_different": 88.16461563110352,
"n_different": 7395784,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.24.mlp.experts.down_proj",
"max_abs_diff": 0.0382080078125,
"mean_abs_diff": 0.00016885525838006288,
"pct_different": 84.98790711164474,
"n_different": 228137676,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.24.mlp.experts.gate_up_proj",
"max_abs_diff": 0.009571075439453125,
"mean_abs_diff": 7.079898932715878e-05,
"pct_different": 78.11102215200663,
"n_different": 419355357,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.24.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.24.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0123138427734375,
"mean_abs_diff": 0.0001695990067673847,
"pct_different": 85.58683395385742,
"n_different": 897443,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.24.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0130767822265625,
"mean_abs_diff": 0.00018669612472876906,
"pct_different": 91.02592468261719,
"n_different": 954476,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.24.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.001514434814453125,
"mean_abs_diff": 6.762769044144079e-05,
"pct_different": 79.97007369995117,
"n_different": 838547,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.24.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0050048828125,
"mean_abs_diff": 0.0004709986096713692,
"pct_different": 98.6328125,
"n_different": 2020,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.24.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.25.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.25.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 6.28642737865448e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.25.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.25.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.25.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000762939453125,
"mean_abs_diff": 9.0843575890176e-05,
"pct_different": 77.24456787109375,
"n_different": 50623,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.25.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 7.25840509403497e-05,
"pct_different": 79.03594970703125,
"n_different": 51797,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.25.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 9.110737300943583e-05,
"pct_different": 75.72745680809021,
"n_different": 12704959,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.25.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 7.248125621117651e-05,
"pct_different": 75.85275173187256,
"n_different": 6362990,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.25.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.25.linear_attn.out_proj.weight",
"max_abs_diff": 0.0540771484375,
"mean_abs_diff": 0.000518718094099313,
"pct_different": 87.50219345092773,
"n_different": 7340216,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.25.mlp.experts.down_proj",
"max_abs_diff": 0.0317840576171875,
"mean_abs_diff": 0.0001698803826002404,
"pct_different": 84.8406694829464,
"n_different": 227742438,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.25.mlp.experts.gate_up_proj",
"max_abs_diff": 0.01165771484375,
"mean_abs_diff": 7.39435781724751e-05,
"pct_different": 78.39019447565079,
"n_different": 420854152,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.25.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.25.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.012664794921875,
"mean_abs_diff": 0.0001598140806891024,
"pct_different": 87.34731674194336,
"n_different": 915903,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.25.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.010009765625,
"mean_abs_diff": 0.0001573283807374537,
"pct_different": 89.9637222290039,
"n_different": 943338,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.25.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0064697265625,
"mean_abs_diff": 0.00011051571345888078,
"pct_different": 84.61780548095703,
"n_different": 887282,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.25.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.005584716796875,
"mean_abs_diff": 0.0005265480722300708,
"pct_different": 99.12109375,
"n_different": 2030,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.25.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.26.input_layernorm.weight",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 2.9103830456733704e-11,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.26.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 1.0710209608078003e-08,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.26.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.26.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.26.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 9.177508763968945e-05,
"pct_different": 77.2705078125,
"n_different": 50640,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.26.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 7.805024506524205e-05,
"pct_different": 79.03900146484375,
"n_different": 51799,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.26.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.0018310546875,
"mean_abs_diff": 9.564950596541166e-05,
"pct_different": 76.42055153846741,
"n_different": 12821241,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.26.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.0013427734375,
"mean_abs_diff": 6.661845691269264e-05,
"pct_different": 75.66145658493042,
"n_different": 6346943,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.26.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.26.linear_attn.out_proj.weight",
"max_abs_diff": 0.0650634765625,
"mean_abs_diff": 0.0005140916327945888,
"pct_different": 87.78066635131836,
"n_different": 7363576,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.26.mlp.experts.down_proj",
"max_abs_diff": 0.02740478515625,
"mean_abs_diff": 0.00017445073171984404,
"pct_different": 84.93271432816982,
"n_different": 227989519,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.26.mlp.experts.gate_up_proj",
"max_abs_diff": 0.01071929931640625,
"mean_abs_diff": 7.931649452075362e-05,
"pct_different": 78.86200547218323,
"n_different": 423387168,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.26.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.26.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0098419189453125,
"mean_abs_diff": 0.00016686832532286644,
"pct_different": 86.50693893432617,
"n_different": 907091,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.26.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.01220703125,
"mean_abs_diff": 0.00018885653116740286,
"pct_different": 91.31221771240234,
"n_different": 957478,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.26.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0029296875,
"mean_abs_diff": 7.671593630220741e-05,
"pct_different": 81.4016342163086,
"n_different": 853558,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.26.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0040283203125,
"mean_abs_diff": 0.00037974317092448473,
"pct_different": 98.73046875,
"n_different": 2022,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.26.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.27.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.27.mlp.experts.down_proj",
"max_abs_diff": 0.03814697265625,
"mean_abs_diff": 0.0001794793497538194,
"pct_different": 85.1216472685337,
"n_different": 228496682,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.27.mlp.experts.gate_up_proj",
"max_abs_diff": 0.012451171875,
"mean_abs_diff": 5.746708484366536e-05,
"pct_different": 55.09844906628132,
"n_different": 295807546,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.27.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.27.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0107421875,
"mean_abs_diff": 0.0001975538325496018,
"pct_different": 85.57443618774414,
"n_different": 897313,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.27.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.018798828125,
"mean_abs_diff": 0.0002619295846670866,
"pct_different": 92.55857467651367,
"n_different": 970547,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.27.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00103759765625,
"mean_abs_diff": 5.918543683947064e-05,
"pct_different": 78.31268310546875,
"n_different": 821168,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.27.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.00469970703125,
"mean_abs_diff": 0.0004430483386386186,
"pct_different": 98.828125,
"n_different": 2024,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.27.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.27.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.27.self_attn.k_proj.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 7.92950377217494e-05,
"pct_different": 75.97541809082031,
"n_different": 796660,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.27.self_attn.o_proj.weight",
"max_abs_diff": 0.032196044921875,
"mean_abs_diff": 0.00032847755937837064,
"pct_different": 85.68580150604248,
"n_different": 7187846,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.27.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.27.self_attn.q_proj.weight",
"max_abs_diff": 0.00115966796875,
"mean_abs_diff": 7.270420610439032e-05,
"pct_different": 75.59701800346375,
"n_different": 12683075,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.27.self_attn.v_proj.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 6.744181155227125e-05,
"pct_different": 76.58853530883789,
"n_different": 803089,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.28.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.28.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 9.778887033462524e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.28.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.28.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.28.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.00079345703125,
"mean_abs_diff": 9.187695832224563e-05,
"pct_different": 77.9815673828125,
"n_different": 51106,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.28.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 7.891813584137708e-05,
"pct_different": 79.23736572265625,
"n_different": 51929,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.28.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.002197265625,
"mean_abs_diff": 9.18437508516945e-05,
"pct_different": 75.92564225196838,
"n_different": 12738209,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.28.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001495361328125,
"mean_abs_diff": 6.9412897573784e-05,
"pct_different": 75.61913728713989,
"n_different": 6343393,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.28.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.28.linear_attn.out_proj.weight",
"max_abs_diff": 0.03228759765625,
"mean_abs_diff": 0.0005236981087364256,
"pct_different": 87.35791444778442,
"n_different": 7328113,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.28.mlp.experts.down_proj",
"max_abs_diff": 0.0270233154296875,
"mean_abs_diff": 0.00016920926282182336,
"pct_different": 84.75274406373501,
"n_different": 227506415,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.28.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0153656005859375,
"mean_abs_diff": 8.473411435261369e-05,
"pct_different": 79.3907668441534,
"n_different": 426225934,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.28.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.28.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.013580322265625,
"mean_abs_diff": 0.00021053112868685275,
"pct_different": 85.90002059936523,
"n_different": 900727,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.28.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.016845703125,
"mean_abs_diff": 0.00021755343186669052,
"pct_different": 91.11166000366211,
"n_different": 955375,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.28.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00133514404296875,
"mean_abs_diff": 6.017617124598473e-05,
"pct_different": 78.37247848510742,
"n_different": 821795,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.28.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0042724609375,
"mean_abs_diff": 0.00040127639658749104,
"pct_different": 98.73046875,
"n_different": 2022,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.28.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.29.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.29.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 1.1874362826347351e-08,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.29.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.29.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.29.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 8.780425559962168e-05,
"pct_different": 77.6641845703125,
"n_different": 50898,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.29.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.000518798828125,
"mean_abs_diff": 7.96613676357083e-05,
"pct_different": 78.70025634765625,
"n_different": 51577,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.29.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001708984375,
"mean_abs_diff": 9.18063087738119e-05,
"pct_different": 76.07945799827576,
"n_different": 12764015,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.29.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 6.873485108371824e-05,
"pct_different": 75.67347288131714,
"n_different": 6347951,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.29.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.29.linear_attn.out_proj.weight",
"max_abs_diff": 0.050506591796875,
"mean_abs_diff": 0.000531617144588381,
"pct_different": 87.65290975570679,
"n_different": 7352859,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.29.mlp.experts.down_proj",
"max_abs_diff": 0.02685546875,
"mean_abs_diff": 0.00016401131870225072,
"pct_different": 84.61188152432442,
"n_different": 227128290,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.29.mlp.experts.gate_up_proj",
"max_abs_diff": 0.015777587890625,
"mean_abs_diff": 6.107890658313408e-05,
"pct_different": 56.84496387839317,
"n_different": 305184076,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.29.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.29.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.024078369140625,
"mean_abs_diff": 0.00017707540246192366,
"pct_different": 86.66009902954102,
"n_different": 908697,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.29.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.010097384452819824,
"mean_abs_diff": 0.00020580603450071067,
"pct_different": 87.35103607177734,
"n_different": 915942,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.29.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00262451171875,
"mean_abs_diff": 5.184086330700666e-05,
"pct_different": 62.17975616455078,
"n_different": 652002,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.29.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0035400390625,
"mean_abs_diff": 0.00033361499663442373,
"pct_different": 98.583984375,
"n_different": 2019,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.29.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.3.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.3.mlp.experts.down_proj",
"max_abs_diff": 0.0020294189453125,
"mean_abs_diff": 4.4209707994014025e-05,
"pct_different": 74.01256300508976,
"n_different": 198675961,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.3.mlp.experts.gate_up_proj",
"max_abs_diff": 0.00079345703125,
"mean_abs_diff": 4.3694086343748495e-05,
"pct_different": 74.10692442208529,
"n_different": 397858521,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.3.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.3.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001708984375,
"mean_abs_diff": 5.025587233831175e-05,
"pct_different": 76.22089385986328,
"n_different": 799234,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.3.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.00079345703125,
"mean_abs_diff": 5.049067476647906e-05,
"pct_different": 76.59769058227539,
"n_different": 803185,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.3.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.000518798828125,
"mean_abs_diff": 5.181989399716258e-05,
"pct_different": 76.29032135009766,
"n_different": 799962,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.3.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.3.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.3.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.3.self_attn.k_proj.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 6.530997964659946e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.3.self_attn.o_proj.weight",
"max_abs_diff": 0.002197265625,
"mean_abs_diff": 6.437394040403888e-05,
"pct_different": 75.57034492492676,
"n_different": 6339300,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.3.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.3.self_attn.q_proj.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 6.194018388472333e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.3.self_attn.v_proj.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 9.981127035985082e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.30.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.30.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 8.149072527885437e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.30.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.30.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.30.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 9.039473661687225e-05,
"pct_different": 77.5238037109375,
"n_different": 50806,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.30.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.000640869140625,
"mean_abs_diff": 8.33064696053043e-05,
"pct_different": 78.95965576171875,
"n_different": 51747,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.30.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 9.462613525101915e-05,
"pct_different": 76.13858580589294,
"n_different": 12773935,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.30.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 6.901209417264909e-05,
"pct_different": 75.79432725906372,
"n_different": 6358089,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.30.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.30.linear_attn.out_proj.weight",
"max_abs_diff": 0.0516357421875,
"mean_abs_diff": 0.000501302070915699,
"pct_different": 87.40135431289673,
"n_different": 7331757,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.30.mlp.experts.down_proj",
"max_abs_diff": 0.02935791015625,
"mean_abs_diff": 0.00016379347653128207,
"pct_different": 84.55454334616661,
"n_different": 226974374,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.30.mlp.experts.gate_up_proj",
"max_abs_diff": 0.014862060546875,
"mean_abs_diff": 6.591484998352826e-05,
"pct_different": 57.95666594058275,
"n_different": 311152481,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.30.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.30.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0145263671875,
"mean_abs_diff": 0.00019252604397479445,
"pct_different": 85.81275939941406,
"n_different": 899812,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.30.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.018218994140625,
"mean_abs_diff": 0.000250937941018492,
"pct_different": 88.23652267456055,
"n_different": 925227,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.30.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0015869140625,
"mean_abs_diff": 1.9374905605218373e-05,
"pct_different": 42.94710159301758,
"n_different": 450333,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.30.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0037841796875,
"mean_abs_diff": 0.00035779309109784663,
"pct_different": 98.486328125,
"n_different": 2017,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.30.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.31.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.31.mlp.experts.down_proj",
"max_abs_diff": 0.028594970703125,
"mean_abs_diff": 0.00016276071255560964,
"pct_different": 84.3730952590704,
"n_different": 226487303,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.31.mlp.experts.gate_up_proj",
"max_abs_diff": 0.015411376953125,
"mean_abs_diff": 7.159714732551947e-05,
"pct_different": 58.91194976866245,
"n_different": 316281122,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.31.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.31.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.00853729248046875,
"mean_abs_diff": 0.0001893887238111347,
"pct_different": 85.7656478881836,
"n_different": 899318,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.31.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0130615234375,
"mean_abs_diff": 0.0002684254141058773,
"pct_different": 88.7507438659668,
"n_different": 930619,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.31.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 2.147901432181243e-05,
"pct_different": 46.35343551635742,
"n_different": 486051,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.31.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.00372314453125,
"mean_abs_diff": 0.0003477830032352358,
"pct_different": 98.73046875,
"n_different": 2022,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.31.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.31.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.31.self_attn.k_proj.weight",
"max_abs_diff": 0.0008544921875,
"mean_abs_diff": 8.076215453911573e-05,
"pct_different": 75.84085464477539,
"n_different": 795249,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.31.self_attn.o_proj.weight",
"max_abs_diff": 0.02266097068786621,
"mean_abs_diff": 0.00023742503253743052,
"pct_different": 84.36301946640015,
"n_different": 7076883,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.31.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.31.self_attn.q_proj.weight",
"max_abs_diff": 0.001495361328125,
"mean_abs_diff": 7.578008808195591e-05,
"pct_different": 75.57690143585205,
"n_different": 12679700,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.31.self_attn.v_proj.weight",
"max_abs_diff": 0.00103759765625,
"mean_abs_diff": 7.029892003629357e-05,
"pct_different": 77.0151138305664,
"n_different": 807562,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.32.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.32.linear_attn.A_log",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 4.889443516731262e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.32.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.32.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.32.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 9.101589967031032e-05,
"pct_different": 77.78778076171875,
"n_different": 50979,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.32.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 7.679347618250176e-05,
"pct_different": 78.61328125,
"n_different": 51520,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.32.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.0023193359375,
"mean_abs_diff": 9.238612256012857e-05,
"pct_different": 76.15182399749756,
"n_different": 12776156,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.32.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.0013427734375,
"mean_abs_diff": 7.127261778805405e-05,
"pct_different": 75.95806121826172,
"n_different": 6371824,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.32.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.32.linear_attn.out_proj.weight",
"max_abs_diff": 0.003387451171875,
"mean_abs_diff": 7.740223372820765e-05,
"pct_different": 75.6868839263916,
"n_different": 6349076,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.32.mlp.experts.down_proj",
"max_abs_diff": 0.02142333984375,
"mean_abs_diff": 0.00015576885198242962,
"pct_different": 84.24240611493587,
"n_different": 226136487,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.32.mlp.experts.gate_up_proj",
"max_abs_diff": 0.01526641845703125,
"mean_abs_diff": 7.210462354123592e-05,
"pct_different": 60.03406420350075,
"n_different": 322305428,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.32.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.32.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.00726318359375,
"mean_abs_diff": 0.00015654056915082037,
"pct_different": 88.17319869995117,
"n_different": 924563,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.32.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.005889892578125,
"mean_abs_diff": 0.00010276605462422594,
"pct_different": 80.1513671875,
"n_different": 840448,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.32.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00909423828125,
"mean_abs_diff": 0.0001641318085603416,
"pct_different": 81.64424896240234,
"n_different": 856102,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.32.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.00238037109375,
"mean_abs_diff": 0.00022551114670932293,
"pct_different": 97.998046875,
"n_different": 2007,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.32.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.33.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.33.linear_attn.A_log",
"max_abs_diff": 4.470348358154297e-08,
"mean_abs_diff": 7.450580596923828e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.33.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.33.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.33.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 9.000087447930127e-05,
"pct_different": 77.77099609375,
"n_different": 50968,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.33.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 7.215674850158393e-05,
"pct_different": 77.69927978515625,
"n_different": 50921,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.33.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 9.3386261141859e-05,
"pct_different": 76.09735131263733,
"n_different": 12767017,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.33.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 7.20742391422391e-05,
"pct_different": 75.771164894104,
"n_different": 6356146,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.33.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.33.linear_attn.out_proj.weight",
"max_abs_diff": 0.003662109375,
"mean_abs_diff": 7.798991282470524e-05,
"pct_different": 75.65804719924927,
"n_different": 6346657,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.33.mlp.experts.down_proj",
"max_abs_diff": 0.019369125366210938,
"mean_abs_diff": 0.00015237636398524046,
"pct_different": 84.0511217713356,
"n_different": 225623012,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.33.mlp.experts.gate_up_proj",
"max_abs_diff": 0.01514434814453125,
"mean_abs_diff": 7.405649375868961e-05,
"pct_different": 60.37269998341799,
"n_different": 324123465,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.33.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.33.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.01397705078125,
"mean_abs_diff": 0.0001608088205102831,
"pct_different": 85.75677871704102,
"n_different": 899225,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.33.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.013822555541992188,
"mean_abs_diff": 0.0002342966035939753,
"pct_different": 87.44077682495117,
"n_different": 916883,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.33.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00341796875,
"mean_abs_diff": 5.740391497965902e-05,
"pct_different": 64.68057632446289,
"n_different": 678225,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.33.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.00164794921875,
"mean_abs_diff": 0.00015396288654301316,
"pct_different": 96.875,
"n_different": 1984,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.33.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.34.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.34.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 1.4784745872020721e-08,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.34.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.34.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.34.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 0.00010084414680022746,
"pct_different": 77.2125244140625,
"n_different": 50602,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.34.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 7.188737799879164e-05,
"pct_different": 76.93328857421875,
"n_different": 50419,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.34.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 9.46048749028705e-05,
"pct_different": 76.37377977371216,
"n_different": 12813394,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.34.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 7.370914681814611e-05,
"pct_different": 75.92724561691284,
"n_different": 6369239,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.34.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.34.linear_attn.out_proj.weight",
"max_abs_diff": 0.00390625,
"mean_abs_diff": 8.248243102570996e-05,
"pct_different": 76.42189264297485,
"n_different": 6410733,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.34.mlp.experts.down_proj",
"max_abs_diff": 0.02142333984375,
"mean_abs_diff": 0.00015174713917076588,
"pct_different": 84.09503288567066,
"n_different": 225740885,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.34.mlp.experts.gate_up_proj",
"max_abs_diff": 0.015228271484375,
"mean_abs_diff": 7.801589526934549e-05,
"pct_different": 61.49240620434284,
"n_different": 330134842,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.34.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.34.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.013916015625,
"mean_abs_diff": 0.00015560949395876378,
"pct_different": 66.48197174072266,
"n_different": 697114,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.34.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.02081298828125,
"mean_abs_diff": 0.00024355290224775672,
"pct_different": 87.3295783996582,
"n_different": 915717,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.34.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.002197265625,
"mean_abs_diff": 2.233486156910658e-05,
"pct_different": 46.485328674316406,
"n_different": 487434,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.34.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0013427734375,
"mean_abs_diff": 0.00012425615568645298,
"pct_different": 96.435546875,
"n_different": 1975,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.34.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.35.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.35.mlp.experts.down_proj",
"max_abs_diff": 0.02032470703125,
"mean_abs_diff": 0.00016059938934631646,
"pct_different": 84.20781157910824,
"n_different": 226043623,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.35.mlp.experts.gate_up_proj",
"max_abs_diff": 0.017578125,
"mean_abs_diff": 8.783558587310836e-05,
"pct_different": 62.8320237621665,
"n_different": 337326859,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.35.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.35.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.01200103759765625,
"mean_abs_diff": 0.00017338157340418547,
"pct_different": 68.32456588745117,
"n_different": 716435,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.35.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.01861572265625,
"mean_abs_diff": 0.00028769392520189285,
"pct_different": 87.29629516601562,
"n_different": 915368,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.35.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0015869140625,
"mean_abs_diff": 2.2541513317264616e-05,
"pct_different": 45.790672302246094,
"n_different": 480150,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.35.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0013427734375,
"mean_abs_diff": 0.00012546921789180487,
"pct_different": 96.240234375,
"n_different": 1971,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.35.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.35.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.35.self_attn.k_proj.weight",
"max_abs_diff": 0.00115966796875,
"mean_abs_diff": 8.050930046010762e-05,
"pct_different": 76.22861862182617,
"n_different": 799315,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.35.self_attn.o_proj.weight",
"max_abs_diff": 0.0162353515625,
"mean_abs_diff": 0.00020530851907096803,
"pct_different": 83.65904092788696,
"n_different": 7017829,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.35.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.35.self_attn.q_proj.weight",
"max_abs_diff": 0.00164794921875,
"mean_abs_diff": 7.766791532048956e-05,
"pct_different": 75.8864164352417,
"n_different": 12731628,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.35.self_attn.v_proj.weight",
"max_abs_diff": 0.00146484375,
"mean_abs_diff": 9.362241689814255e-05,
"pct_different": 78.76205444335938,
"n_different": 825880,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.36.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.36.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 7.916241884231567e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.36.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.36.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.36.linear_attn.in_proj_a.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 7.808864666003501e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.36.linear_attn.in_proj_b.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 9.961809155356605e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.36.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 4.946612564005193e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.36.linear_attn.in_proj_z.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 7.247678152078052e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.36.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.36.linear_attn.out_proj.weight",
"max_abs_diff": 0.00830078125,
"mean_abs_diff": 7.979055226314813e-05,
"pct_different": 76.34977102279663,
"n_different": 6404683,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.36.mlp.experts.down_proj",
"max_abs_diff": 0.01799774169921875,
"mean_abs_diff": 0.00016030555707402527,
"pct_different": 84.20749418437481,
"n_different": 226042771,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.36.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0145263671875,
"mean_abs_diff": 8.27742405817844e-05,
"pct_different": 61.87529023736715,
"n_different": 332190435,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.36.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.36.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.006591796875,
"mean_abs_diff": 0.00014604577154386789,
"pct_different": 87.18204498291016,
"n_different": 914170,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.36.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.013515472412109375,
"mean_abs_diff": 0.00017460605886299163,
"pct_different": 81.44760131835938,
"n_different": 854040,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.36.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.005859375,
"mean_abs_diff": 0.00012355484068393707,
"pct_different": 78.62024307250977,
"n_different": 824393,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.36.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.001190185546875,
"mean_abs_diff": 0.00011287422967143357,
"pct_different": 95.654296875,
"n_different": 1959,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.36.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.37.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.37.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 1.1816155165433884e-08,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.37.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.37.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.37.linear_attn.in_proj_a.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 8.164136033883551e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.37.linear_attn.in_proj_b.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 8.036238341446733e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.37.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 4.976379551491217e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.37.linear_attn.in_proj_z.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 7.754229550127612e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.37.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.37.linear_attn.out_proj.weight",
"max_abs_diff": 0.00244140625,
"mean_abs_diff": 8.255692955572158e-05,
"pct_different": 76.73879861831665,
"n_different": 6437317,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.37.mlp.experts.down_proj",
"max_abs_diff": 0.01904296875,
"mean_abs_diff": 0.00016294344095513225,
"pct_different": 84.27763022482395,
"n_different": 226231041,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.37.mlp.experts.gate_up_proj",
"max_abs_diff": 0.016576766967773438,
"mean_abs_diff": 7.902195648057386e-05,
"pct_different": 61.08949836343527,
"n_different": 327971747,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.37.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.37.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.01202392578125,
"mean_abs_diff": 0.000136027651024051,
"pct_different": 80.70955276489258,
"n_different": 846301,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.37.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.01483154296875,
"mean_abs_diff": 0.00019479072943795472,
"pct_different": 82.67087936401367,
"n_different": 866867,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.37.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0091094970703125,
"mean_abs_diff": 0.00011996040120720863,
"pct_different": 76.99165344238281,
"n_different": 807316,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.37.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.000457763671875,
"mean_abs_diff": 4.295829057809897e-05,
"pct_different": 89.2578125,
"n_different": 1828,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.37.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.38.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.38.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 1.6298145055770874e-08,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.38.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.38.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.38.linear_attn.in_proj_a.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 6.195932655828074e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.38.linear_attn.in_proj_b.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 5.9685589803848416e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.38.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 5.123578644683491e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.38.linear_attn.in_proj_z.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 7.192431546176881e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.38.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.38.linear_attn.out_proj.weight",
"max_abs_diff": 0.002197265625,
"mean_abs_diff": 7.896935130702332e-05,
"pct_different": 76.81151628494263,
"n_different": 6443417,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.38.mlp.experts.down_proj",
"max_abs_diff": 0.02142810821533203,
"mean_abs_diff": 0.00016490135749336332,
"pct_different": 84.44033712148666,
"n_different": 226667804,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.38.mlp.experts.gate_up_proj",
"max_abs_diff": 0.012939453125,
"mean_abs_diff": 7.53445565351285e-05,
"pct_different": 60.249427892267704,
"n_different": 323461653,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.38.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.38.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.01220703125,
"mean_abs_diff": 0.0001475134922657162,
"pct_different": 74.07846450805664,
"n_different": 776769,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.38.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0196533203125,
"mean_abs_diff": 0.00026799453189596534,
"pct_different": 85.18447875976562,
"n_different": 893224,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.38.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00439453125,
"mean_abs_diff": 4.584606722346507e-05,
"pct_different": 59.99946594238281,
"n_different": 629140,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.38.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.000579833984375,
"mean_abs_diff": 5.4790929425507784e-05,
"pct_different": 93.65234375,
"n_different": 1918,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.38.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.39.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.39.mlp.experts.down_proj",
"max_abs_diff": 0.020599365234375,
"mean_abs_diff": 0.00015861380961723626,
"pct_different": 84.2293206602335,
"n_different": 226101361,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.39.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0125579833984375,
"mean_abs_diff": 6.997332820901647e-05,
"pct_different": 58.380261063575745,
"n_different": 313426640,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.39.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.39.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.010498046875,
"mean_abs_diff": 0.0001098875145544298,
"pct_different": 65.07434844970703,
"n_different": 682354,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.39.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0133056640625,
"mean_abs_diff": 0.0002619568258523941,
"pct_different": 87.41598129272461,
"n_different": 916623,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.39.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.002197265625,
"mean_abs_diff": 1.3912536815041676e-05,
"pct_different": 37.54701614379883,
"n_different": 393709,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.39.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.000579833984375,
"mean_abs_diff": 5.540027632378042e-05,
"pct_different": 92.138671875,
"n_different": 1887,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.39.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.39.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.39.self_attn.k_proj.weight",
"max_abs_diff": 0.00091552734375,
"mean_abs_diff": 8.063699351623654e-05,
"pct_different": 79.56247329711914,
"n_different": 834273,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.39.self_attn.o_proj.weight",
"max_abs_diff": 0.0020751953125,
"mean_abs_diff": 7.997776265256107e-05,
"pct_different": 76.9538402557373,
"n_different": 6455356,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.39.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.39.self_attn.q_proj.weight",
"max_abs_diff": 0.0015869140625,
"mean_abs_diff": 7.685480522923172e-05,
"pct_different": 75.80427527427673,
"n_different": 12717847,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.39.self_attn.v_proj.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 7.297185220522806e-05,
"pct_different": 79.07142639160156,
"n_different": 829124,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.4.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.4.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 1.2863893061876297e-08,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.4.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.4.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.4.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 8.83650645846501e-05,
"pct_different": 76.54266357421875,
"n_different": 50163,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.4.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 6.650891009485349e-05,
"pct_different": 77.3834228515625,
"n_different": 50714,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001068115234375,
"mean_abs_diff": 7.469176489394158e-05,
"pct_different": 75.51474571228027,
"n_different": 12669272,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.4.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.0010986328125,
"mean_abs_diff": 6.896830745972693e-05,
"pct_different": 75.60737133026123,
"n_different": 6342406,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.4.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.4.linear_attn.out_proj.weight",
"max_abs_diff": 0.0029296875,
"mean_abs_diff": 6.950877286726609e-05,
"pct_different": 75.49833059310913,
"n_different": 6333259,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.4.mlp.experts.down_proj",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.400653415359557e-05,
"pct_different": 74.13872145116329,
"n_different": 199014615,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.4.mlp.experts.gate_up_proj",
"max_abs_diff": 0.00091552734375,
"mean_abs_diff": 4.450380947673693e-05,
"pct_different": 74.20840412378311,
"n_different": 398403336,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.4.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.4.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 5.0921604270115495e-05,
"pct_different": 75.7965087890625,
"n_different": 794784,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.4.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 4.8473539209226146e-05,
"pct_different": 75.7023811340332,
"n_different": 793797,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.4.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00051116943359375,
"mean_abs_diff": 5.1016599172726274e-05,
"pct_different": 75.72765350341797,
"n_different": 794062,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.4.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.4.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.5.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.5.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 6.51925802230835e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.5.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.5.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.5.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 9.281998791266233e-05,
"pct_different": 76.58538818359375,
"n_different": 50191,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.5.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 6.878112617414445e-05,
"pct_different": 77.9052734375,
"n_different": 51056,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001251220703125,
"mean_abs_diff": 7.507378177251667e-05,
"pct_different": 75.54700970649719,
"n_different": 12674685,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.5.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.0010986328125,
"mean_abs_diff": 6.772989581804723e-05,
"pct_different": 75.43255090713501,
"n_different": 6327741,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.5.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.5.linear_attn.out_proj.weight",
"max_abs_diff": 0.0029296875,
"mean_abs_diff": 6.921568274265155e-05,
"pct_different": 75.57656764984131,
"n_different": 6339822,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.5.mlp.experts.down_proj",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.41000702267047e-05,
"pct_different": 74.24795851111412,
"n_different": 199307846,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.5.mlp.experts.gate_up_proj",
"max_abs_diff": 0.000762939453125,
"mean_abs_diff": 4.478307528188452e-05,
"pct_different": 74.30660780519247,
"n_different": 398930563,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.5.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.5.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001953125,
"mean_abs_diff": 5.1026254368480295e-05,
"pct_different": 76.6988754272461,
"n_different": 804246,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.5.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 4.81239112559706e-05,
"pct_different": 76.41477584838867,
"n_different": 801267,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.5.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00043487548828125,
"mean_abs_diff": 5.2817369578406215e-05,
"pct_different": 76.38359069824219,
"n_different": 800940,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.5.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.5.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.6.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.6.linear_attn.A_log",
"max_abs_diff": 4.470348358154297e-08,
"mean_abs_diff": 1.0710209608078003e-08,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.6.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.6.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.6.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000640869140625,
"mean_abs_diff": 9.177657193504274e-05,
"pct_different": 77.56805419921875,
"n_different": 50835,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.6.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.000640869140625,
"mean_abs_diff": 7.389762322418392e-05,
"pct_different": 77.65655517578125,
"n_different": 50893,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.00152587890625,
"mean_abs_diff": 7.546762935817242e-05,
"pct_different": 75.68546533584595,
"n_different": 12697914,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.6.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001068115234375,
"mean_abs_diff": 6.465703336289153e-05,
"pct_different": 75.33910274505615,
"n_different": 6319902,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.6.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.6.linear_attn.out_proj.weight",
"max_abs_diff": 0.00244140625,
"mean_abs_diff": 6.946274515939876e-05,
"pct_different": 75.57202577590942,
"n_different": 6339441,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.6.mlp.experts.down_proj",
"max_abs_diff": 0.0010986328125,
"mean_abs_diff": 4.4040236389264464e-05,
"pct_different": 74.26761761307716,
"n_different": 199360618,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.6.mlp.experts.gate_up_proj",
"max_abs_diff": 0.000885009765625,
"mean_abs_diff": 4.483235170482658e-05,
"pct_different": 74.34323616325855,
"n_different": 399127210,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.6.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.6.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0013427734375,
"mean_abs_diff": 5.054691428085789e-05,
"pct_different": 76.48334503173828,
"n_different": 801986,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.6.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.000579833984375,
"mean_abs_diff": 4.508010169956833e-05,
"pct_different": 76.05876922607422,
"n_different": 797534,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.6.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00042724609375,
"mean_abs_diff": 5.27710399182979e-05,
"pct_different": 76.43842697143555,
"n_different": 801515,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.6.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.6.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.7.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "model.language_model.layers.7.mlp.experts.down_proj",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 4.385596184874885e-05,
"pct_different": 74.2759820073843,
"n_different": 199383071,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.7.mlp.experts.gate_up_proj",
"max_abs_diff": 0.000762939453125,
"mean_abs_diff": 4.485074896365404e-05,
"pct_different": 74.34071283787489,
"n_different": 399113663,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.7.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.7.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001708984375,
"mean_abs_diff": 4.968056236975826e-05,
"pct_different": 76.46045684814453,
"n_different": 801746,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.7.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.000885009765625,
"mean_abs_diff": 4.494099266594276e-05,
"pct_different": 76.3819694519043,
"n_different": 800923,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.7.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00103759765625,
"mean_abs_diff": 5.288419561111368e-05,
"pct_different": 76.5451431274414,
"n_different": 802634,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.7.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.7.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "model.language_model.layers.7.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "model.language_model.layers.7.self_attn.k_proj.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 6.285083564705474e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "model.language_model.layers.7.self_attn.o_proj.weight",
"max_abs_diff": 0.00244140625,
"mean_abs_diff": 6.5006417571567e-05,
"pct_different": 75.3846526145935,
"n_different": 6323723,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "model.language_model.layers.7.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "model.language_model.layers.7.self_attn.q_proj.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 6.617169919648225e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "model.language_model.layers.7.self_attn.v_proj.weight",
"max_abs_diff": 2.9802322387695312e-08,
"mean_abs_diff": 8.006928453596629e-12,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1048576
},
{
"group": "layernorm",
"name": "model.language_model.layers.8.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.8.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 4.6566128730773926e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.8.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.8.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.8.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.000732421875,
"mean_abs_diff": 9.66722727753222e-05,
"pct_different": 75.860595703125,
"n_different": 49716,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.8.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.0006103515625,
"mean_abs_diff": 6.55977928545326e-05,
"pct_different": 78.67279052734375,
"n_different": 51559,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001220703125,
"mean_abs_diff": 7.933635788504034e-05,
"pct_different": 75.98904371261597,
"n_different": 12748846,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.8.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001312255859375,
"mean_abs_diff": 6.948431837372482e-05,
"pct_different": 75.94003677368164,
"n_different": 6370312,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.8.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.8.linear_attn.out_proj.weight",
"max_abs_diff": 0.00244140625,
"mean_abs_diff": 6.78777796565555e-05,
"pct_different": 75.68689584732056,
"n_different": 6349077,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.8.mlp.experts.down_proj",
"max_abs_diff": 0.0010986328125,
"mean_abs_diff": 4.354276825324632e-05,
"pct_different": 74.25640597939491,
"n_different": 199330522,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.8.mlp.experts.gate_up_proj",
"max_abs_diff": 0.00079345703125,
"mean_abs_diff": 4.480083953239955e-05,
"pct_different": 74.33711122721434,
"n_different": 399094327,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.8.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.8.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001708984375,
"mean_abs_diff": 5.0442882638890296e-05,
"pct_different": 76.84669494628906,
"n_different": 805796,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.8.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0008544921875,
"mean_abs_diff": 4.7637138777645305e-05,
"pct_different": 76.8341064453125,
"n_different": 805664,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.8.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00048828125,
"mean_abs_diff": 5.369909922592342e-05,
"pct_different": 77.0660400390625,
"n_different": 808096,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.8.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.8.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.9.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "linear_attn.A_log",
"name": "model.language_model.layers.9.linear_attn.A_log",
"max_abs_diff": 5.960464477539063e-08,
"mean_abs_diff": 4.773028194904327e-09,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.conv1d",
"name": "model.language_model.layers.9.linear_attn.conv1d.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32768
},
{
"group": "linear_attn.dt_bias",
"name": "model.language_model.layers.9.linear_attn.dt_bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 32
},
{
"group": "linear_attn.in_proj_a",
"name": "model.language_model.layers.9.linear_attn.in_proj_a.weight",
"max_abs_diff": 0.00079345703125,
"mean_abs_diff": 8.912254270398989e-05,
"pct_different": 76.9683837890625,
"n_different": 50442,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_b",
"name": "model.language_model.layers.9.linear_attn.in_proj_b.weight",
"max_abs_diff": 0.000640869140625,
"mean_abs_diff": 7.231815834529698e-05,
"pct_different": 78.3233642578125,
"n_different": 51330,
"total_elements": 65536
},
{
"group": "linear_attn.in_proj_qkv",
"name": "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
"max_abs_diff": 0.001068115234375,
"mean_abs_diff": 7.772062963340431e-05,
"pct_different": 75.87748765945435,
"n_different": 12730130,
"total_elements": 16777216
},
{
"group": "linear_attn.in_proj_z",
"name": "model.language_model.layers.9.linear_attn.in_proj_z.weight",
"max_abs_diff": 0.001007080078125,
"mean_abs_diff": 6.651791773037985e-05,
"pct_different": 75.5383849143982,
"n_different": 6336619,
"total_elements": 8388608
},
{
"group": "linear_attn.norm",
"name": "model.language_model.layers.9.linear_attn.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 128
},
{
"group": "linear_attn.out_proj",
"name": "model.language_model.layers.9.linear_attn.out_proj.weight",
"max_abs_diff": 0.0025634765625,
"mean_abs_diff": 6.690036389045417e-05,
"pct_different": 75.57737827301025,
"n_different": 6339890,
"total_elements": 8388608
},
{
"group": "expert_down",
"name": "model.language_model.layers.9.mlp.experts.down_proj",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.421590710990131e-05,
"pct_different": 74.29834716022015,
"n_different": 199443107,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "model.language_model.layers.9.mlp.experts.gate_up_proj",
"max_abs_diff": 0.000762939453125,
"mean_abs_diff": 4.548922152025625e-05,
"pct_different": 74.4016531854868,
"n_different": 399440834,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "model.language_model.layers.9.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "model.language_model.layers.9.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.001678466796875,
"mean_abs_diff": 4.915479803457856e-05,
"pct_different": 77.23703384399414,
"n_different": 809889,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "model.language_model.layers.9.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0009765625,
"mean_abs_diff": 4.8771180445328355e-05,
"pct_different": 77.30140686035156,
"n_different": 810564,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "model.language_model.layers.9.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.00054931640625,
"mean_abs_diff": 5.2887320634908974e-05,
"pct_different": 77.07967758178711,
"n_different": 808239,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "model.language_model.layers.9.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "model.language_model.layers.9.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "final_norm",
"name": "model.language_model.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "vision",
"name": "model.visual.blocks.0.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.0.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.0.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.0.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.0.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.0.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.0.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.0.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.0.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.0.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.0.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.0.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.1.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.1.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.1.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.1.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.1.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.1.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.1.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.1.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.1.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.1.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.1.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.1.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.10.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.10.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.10.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.10.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.10.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.10.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.10.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.10.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.10.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.10.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.10.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.10.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.11.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.11.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.11.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.11.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.11.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.11.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.11.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.11.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.11.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.11.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.11.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.11.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.12.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.12.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.12.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.12.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.12.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.12.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.12.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.12.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.12.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.12.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.12.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.12.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.13.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.13.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.13.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.13.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.13.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.13.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.13.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.13.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.13.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.13.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.13.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.13.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.14.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.14.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.14.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.14.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.14.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.14.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.14.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.14.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.14.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.14.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.14.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.14.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.15.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.15.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.15.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.15.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.15.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.15.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.15.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.15.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.15.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.15.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.15.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.15.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.16.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.16.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.16.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.16.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.16.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.16.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.16.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.16.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.16.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.16.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.16.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.16.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.17.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.17.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.17.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.17.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.17.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.17.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.17.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.17.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.17.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.17.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.17.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.17.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.18.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.18.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.18.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.18.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.18.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.18.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.18.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.18.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.18.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.18.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.18.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.18.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.19.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.19.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.19.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.19.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.19.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.19.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.19.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.19.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.19.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.19.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.19.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.19.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.2.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.2.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.2.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.2.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.2.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.2.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.2.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.2.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.2.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.2.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.2.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.2.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.20.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.20.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.20.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.20.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.20.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.20.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.20.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.20.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.20.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.20.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.20.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.20.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.21.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.21.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.21.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.21.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.21.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.21.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.21.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.21.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.21.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.21.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.21.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.21.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.22.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.22.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.22.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.22.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.22.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.22.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.22.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.22.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.22.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.22.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.22.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.22.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.23.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.23.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.23.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.23.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.23.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.23.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.23.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.23.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.23.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.23.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.23.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.23.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.24.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.24.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.24.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.24.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.24.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.24.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.24.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.24.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.24.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.24.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.24.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.24.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.25.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.25.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.25.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.25.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.25.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.25.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.25.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.25.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.25.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.25.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.25.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.25.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.26.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.26.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.26.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.26.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.26.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.26.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.26.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.26.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.26.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.26.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.26.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.26.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.3.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.3.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.3.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.3.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.3.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.3.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.3.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.3.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.3.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.3.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.3.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.3.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.4.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.4.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.4.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.4.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.4.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.4.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.4.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.4.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.4.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.4.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.4.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.4.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.5.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.5.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.5.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.5.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.5.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.5.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.5.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.5.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.5.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.5.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.5.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.5.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.6.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.6.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.6.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.6.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.6.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.6.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.6.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.6.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.6.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.6.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.6.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.6.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.7.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.7.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.7.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.7.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.7.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.7.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.7.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.7.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.7.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.7.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.7.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.7.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.8.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.8.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.8.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.8.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.8.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.8.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.8.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.8.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.8.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.8.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.8.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.8.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.9.attn.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.9.attn.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1327104
},
{
"group": "vision",
"name": "model.visual.blocks.9.attn.qkv.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3456
},
{
"group": "vision",
"name": "model.visual.blocks.9.attn.qkv.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 3981312
},
{
"group": "vision",
"name": "model.visual.blocks.9.mlp.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4304
},
{
"group": "vision",
"name": "model.visual.blocks.9.mlp.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.9.mlp.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.9.mlp.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4958208
},
{
"group": "vision",
"name": "model.visual.blocks.9.norm1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.9.norm1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.9.norm2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.blocks.9.norm2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.merger.linear_fc1.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 4608
},
{
"group": "vision",
"name": "model.visual.merger.linear_fc1.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 21233664
},
{
"group": "vision",
"name": "model.visual.merger.linear_fc2.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "vision",
"name": "model.visual.merger.linear_fc2.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 9437184
},
{
"group": "vision",
"name": "model.visual.merger.norm.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.merger.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.patch_embed.proj.bias",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1152
},
{
"group": "vision",
"name": "model.visual.patch_embed.proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1769472
},
{
"group": "vision",
"name": "model.visual.pos_embed.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2654208
},
{
"group": "mtp",
"name": "mtp.fc.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 8388608
},
{
"group": "layernorm",
"name": "mtp.layers.0.input_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "expert_down",
"name": "mtp.layers.0.mlp.experts.down_proj",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 268435456
},
{
"group": "expert_gate_up",
"name": "mtp.layers.0.mlp.experts.gate_up_proj",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 536870912
},
{
"group": "router_gate",
"name": "mtp.layers.0.mlp.gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 524288
},
{
"group": "shared_expert_down",
"name": "mtp.layers.0.mlp.shared_expert.down_proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1048576
},
{
"group": "shared_expert_gate",
"name": "mtp.layers.0.mlp.shared_expert.gate_proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1048576
},
{
"group": "shared_expert_up",
"name": "mtp.layers.0.mlp.shared_expert.up_proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1048576
},
{
"group": "shared_expert_gate_scalar",
"name": "mtp.layers.0.mlp.shared_expert_gate.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "layernorm",
"name": "mtp.layers.0.post_attention_layernorm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "self_attn.k_norm",
"name": "mtp.layers.0.self_attn.k_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.k_proj",
"name": "mtp.layers.0.self_attn.k_proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1048576
},
{
"group": "self_attn.o_proj",
"name": "mtp.layers.0.self_attn.o_proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 8388608
},
{
"group": "self_attn.q_norm",
"name": "mtp.layers.0.self_attn.q_norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 256
},
{
"group": "self_attn.q_proj",
"name": "mtp.layers.0.self_attn.q_proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 16777216
},
{
"group": "self_attn.v_proj",
"name": "mtp.layers.0.self_attn.v_proj.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 1048576
},
{
"group": "mtp",
"name": "mtp.norm.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "mtp",
"name": "mtp.pre_fc_norm_embedding.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
},
{
"group": "mtp",
"name": "mtp.pre_fc_norm_hidden.weight",
"max_abs_diff": 0.0,
"mean_abs_diff": 0.0,
"pct_different": 0.0,
"n_different": 0,
"total_elements": 2048
}
]
}