Upload Qwen2ForCausalLM

config.json

@@ -1,187 +1,30 @@
 {
-  "_name_or_path": "microsoft/Phi-3-small-128k-instruct",
+  "_name_or_path": "./merged_model",
   "architectures": [
-    "Phi3SmallForCausalLM"
+    "Qwen2ForCausalLM"
   ],
-  "attention_bias": false,
-  "attention_dropout_prob": 0.0,
-  "auto_map": {
-    "AutoConfig": "microsoft/Phi-3-small-128k-instruct--configuration_phi3_small.Phi3SmallConfig",
-    "AutoModelForCausalLM": "microsoft/Phi-3-small-128k-instruct--modeling_phi3_small.Phi3SmallForCausalLM",
-    "AutoTokenizer": "microsoft/Phi-3-small-128k-instruct--tokenization_phi3_small.Phi3SmallTokenizer"
-  },
-  "blocksparse_block_size": 64,
-  "blocksparse_homo_head_pattern": false,
-  "blocksparse_num_local_blocks": 16,
-  "blocksparse_triton_kernel_block_size": 64,
-  "blocksparse_vert_stride": 8,
-  "bos_token_id": 100257,
-  "dense_attention_every_n_layers": 2,
-  "embedding_dropout_prob": 0.1,
-  "eos_token_id": 100257,
-  "ff_dim_multiplier": null,
-  "ff_intermediate_size": 14336,
-  "ffn_dropout_prob": 0.1,
-  "gegelu_limit": 20.0,
-  "gegelu_pad_to_256": true,
-  "hidden_act": "gegelu",
-  "hidden_size": 4096,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
   "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
+  "intermediate_size": 18944,
   "max_position_embeddings": 131072,
-  "model_type": "phi3small",
-  "mup_attn_multiplier": 1.0,
-  "mup_embedding_multiplier": 10.0,
-  "mup_use_scaling": true,
-  "mup_width_multiplier": 8.0,
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "original_max_position_embeddings": 8192,
-  "pad_sequence_to_multiple_of_64": true,
-  "reorder_and_upcast_attn": false,
-  "rope_embedding_base": 1000000,
-  "rope_position_scale": 1.0,
-  "rope_scaling": {
-    "long_factor": [
-      1.0,
-      1.01,
-      1.01,
-      1.02,
-      1.04,
-      1.04,
-      1.04,
-      1.05,
-      1.05,
-      1.06,
-      1.07,
-      1.08,
-      1.08,
-      1.08,
-      1.08,
-      1.08,
-      1.08,
-      1.08,
-      1.09,
-      1.09,
-      1.2,
-      2.31,
-      3.76,
-      9.38,
-      10.1,
-      10.8,
-      18.1,
-      25.2,
-      25.3,
-      26.1,
-      26.6,
-      30.2,
-      33.0,
-      41.5,
-      44.4,
-      44.8,
-      50.2,
-      51.9,
-      59.3,
-      62.7,
-      66.1,
-      66.3,
-      85.8,
-      89.3,
-      90.0,
-      99.9,
-      107.0,
-      110.0,
-      111.0,
-      117.0,
-      118.0,
-      121.0,
-      122.0,
-      127.0,
-      127.0,
-      128.0,
-      128.0,
-      128.0,
-      128.0,
-      128.0,
-      128.0,
-      129.0,
-      129.0,
-      129.0
-    ],
-    "long_mscale": 1.1902380714238083,
-    "original_max_position_embeddings": 8192,
-    "short_factor": [
-      1.02,
-      1.02,
-      1.05,
-      1.05,
-      1.06,
-      1.08,
-      1.08,
-      1.08,
-      1.08,
-      1.12,
-      1.1800000000000002,
-      1.1900000000000002,
-      1.1900000000000002,
-      1.2100000000000002,
-      1.2300000000000002,
-      1.2400000000000002,
-      1.2400000000000002,
-      1.2500000000000002,
-      1.3000000000000003,
-      1.3100000000000003,
-      1.4600000000000004,
-      1.5100000000000005,
-      1.7000000000000006,
-      1.9300000000000008,
-      2.080000000000001,
-      2.4399999999999933,
-      3.2199999999999767,
-      3.4499999999999718,
-      3.579999999999969,
-      4.669999999999946,
-      4.779999999999943,
-      5.999999999999917,
-      6.009999999999917,
-      6.4199999999999084,
-      6.619999999999904,
-      7.189999999999892,
-      7.3099999999998895,
-      7.339999999999889,
-      7.479999999999886,
-      9.749999999999837,
-      10.919999999999812,
-      11.219999999999805,
-      11.749999999999794,
-      11.979999999999789,
-      13.239999999999762,
-      13.579999999999755,
-      13.669999999999753,
-      13.82999999999975,
-      14.009999999999746,
-      14.679999999999731,
-      14.889999999999727,
-      15.769999999999708,
-      15.769999999999708,
-      15.819999999999707,
-      15.839999999999707,
-      15.919999999999705,
-      16.029999999999703,
-      16.12999999999972,
-      16.44999999999977,
-      16.44999999999977,
-      16.77999999999982,
-      16.83999999999983,
-      16.83999999999983,
-      16.889999999999837
-    ],
-    "short_mscale": 1.0,
-    "type": "su"
-  },
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
   "use_cache": true,
-  "vocab_size": 100352
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "transformers_version": "4.46.0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c75fcb0f8ff61636d1345f30fe28197d50d58848b059d135c9051f896fe238c
+size 4976687216

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901bbed38953341239b63afb7b9be2bced7e0b3015b37f183aa0964baa82003e
+size 4778622352

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f776f0dc68ce5d7642ac32803a5c6c98f683e16638fe6f66822bebaca9684d75
+size 4932743960

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c203958841c7c08cb13684d94b5c44a2a5209f3dee11318e4af00752e710da5d
+size 4932743992

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2c74beeaa76ead1bc6f54065f730de33dc13bc9936924b627924be7d41b8a2
+size 4998852296

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df346f833753694813b5b4e90cb437f563f9d92309449940a14bb665096ef3e
+size 3662865184

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7dec6ef7f737550b137482c50b15f4426860ab5c14c208701f56af38386fe8a
+size 2179989632

model.safetensors.index.json

@@ -1 +1,346 @@
-{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 15606628352}, "weight_map": {"lm_head.weight": "model-00001-of-00018.safetensors", "model.embed_tokens.weight": "model-00002-of-00018.safetensors", "model.final_layernorm.bias": "model-00002-of-00018.safetensors", "model.final_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.0.input_layernorm.bias": "model-00002-of-00018.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00018.safetensors", "model.layers.0.mlp.down_proj.bias": "model-00002-of-00018.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00018.safetensors", "model.layers.0.mlp.up_proj.bias": "model-00002-of-00018.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.0.post_attention_layernorm.bias": "model-00003-of-00018.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.dense.bias": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.dense.weight": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.query_key_value.bias": "model-00003-of-00018.safetensors", "model.layers.0.self_attn.query_key_value.weight": "model-00003-of-00018.safetensors", "model.layers.1.input_layernorm.bias": "model-00003-of-00018.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.1.mlp.down_proj.bias": "model-00003-of-00018.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.mlp.up_proj.bias": "model-00003-of-00018.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00018.safetensors", "model.layers.1.post_attention_layernorm.bias": "model-00003-of-00018.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.dense.bias": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.dense.weight": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.query_key_value.bias": "model-00003-of-00018.safetensors", "model.layers.1.self_attn.query_key_value.weight": "model-00003-of-00018.safetensors", "model.layers.10.input_layernorm.bias": "model-00003-of-00018.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00018.safetensors", "model.layers.10.mlp.down_proj.bias": "model-00003-of-00018.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00018.safetensors", "model.layers.10.mlp.up_proj.bias": "model-00003-of-00018.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.10.post_attention_layernorm.bias": "model-00004-of-00018.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.dense.bias": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.dense.weight": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.query_key_value.bias": "model-00004-of-00018.safetensors", "model.layers.10.self_attn.query_key_value.weight": "model-00004-of-00018.safetensors", "model.layers.11.input_layernorm.bias": "model-00004-of-00018.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.11.mlp.down_proj.bias": "model-00004-of-00018.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.11.mlp.up_proj.bias": "model-00004-of-00018.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00018.safetensors", "model.layers.11.post_attention_layernorm.bias": "model-00004-of-00018.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.11.self_attn.dense.bias": "model-00004-of-00018.safetensors", "model.layers.11.self_attn.dense.weight": "model-00004-of-00018.safetensors", "model.layers.11.self_attn.query_key_value.bias": "model-00004-of-00018.safetensors", "model.layers.11.self_attn.query_key_value.weight": "model-00004-of-00018.safetensors", "model.layers.12.input_layernorm.bias": "model-00004-of-00018.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00018.safetensors", "model.layers.12.mlp.down_proj.bias": "model-00004-of-00018.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00018.safetensors", "model.layers.12.mlp.up_proj.bias": "model-00004-of-00018.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.12.post_attention_layernorm.bias": "model-00005-of-00018.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.12.self_attn.dense.bias": "model-00005-of-00018.safetensors", "model.layers.12.self_attn.dense.weight": "model-00005-of-00018.safetensors", "model.layers.12.self_attn.query_key_value.bias": "model-00005-of-00018.safetensors", "model.layers.12.self_attn.query_key_value.weight": "model-00005-of-00018.safetensors", "model.layers.13.input_layernorm.bias": "model-00005-of-00018.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.13.mlp.down_proj.bias": "model-00005-of-00018.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.13.mlp.up_proj.bias": "model-00005-of-00018.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00018.safetensors", "model.layers.13.post_attention_layernorm.bias": "model-00005-of-00018.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.13.self_attn.dense.bias": "model-00005-of-00018.safetensors", "model.layers.13.self_attn.dense.weight": "model-00005-of-00018.safetensors", "model.layers.13.self_attn.query_key_value.bias": "model-00005-of-00018.safetensors", "model.layers.13.self_attn.query_key_value.weight": "model-00005-of-00018.safetensors", "model.layers.14.input_layernorm.bias": "model-00005-of-00018.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00018.safetensors", "model.layers.14.mlp.down_proj.bias": "model-00005-of-00018.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00018.safetensors", "model.layers.14.mlp.up_proj.bias": "model-00005-of-00018.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.14.post_attention_layernorm.bias": "model-00006-of-00018.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.14.self_attn.dense.bias": "model-00006-of-00018.safetensors", "model.layers.14.self_attn.dense.weight": "model-00006-of-00018.safetensors", "model.layers.14.self_attn.query_key_value.bias": "model-00006-of-00018.safetensors", "model.layers.14.self_attn.query_key_value.weight": "model-00006-of-00018.safetensors", "model.layers.15.input_layernorm.bias": "model-00006-of-00018.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.15.mlp.down_proj.bias": "model-00006-of-00018.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.15.mlp.up_proj.bias": "model-00006-of-00018.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00018.safetensors", "model.layers.15.post_attention_layernorm.bias": "model-00006-of-00018.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.15.self_attn.dense.bias": "model-00006-of-00018.safetensors", "model.layers.15.self_attn.dense.weight": "model-00006-of-00018.safetensors", "model.layers.15.self_attn.query_key_value.bias": "model-00006-of-00018.safetensors", "model.layers.15.self_attn.query_key_value.weight": "model-00006-of-00018.safetensors", "model.layers.16.input_layernorm.bias": "model-00006-of-00018.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00018.safetensors", "model.layers.16.mlp.down_proj.bias": "model-00006-of-00018.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00018.safetensors", "model.layers.16.mlp.up_proj.bias": "model-00006-of-00018.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.16.post_attention_layernorm.bias": "model-00007-of-00018.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.16.self_attn.dense.bias": "model-00007-of-00018.safetensors", "model.layers.16.self_attn.dense.weight": "model-00007-of-00018.safetensors", "model.layers.16.self_attn.query_key_value.bias": "model-00007-of-00018.safetensors", "model.layers.16.self_attn.query_key_value.weight": "model-00007-of-00018.safetensors", "model.layers.17.input_layernorm.bias": "model-00007-of-00018.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.17.mlp.down_proj.bias": "model-00007-of-00018.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.17.mlp.up_proj.bias": "model-00007-of-00018.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00018.safetensors", "model.layers.17.post_attention_layernorm.bias": "model-00007-of-00018.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.17.self_attn.dense.bias": "model-00007-of-00018.safetensors", "model.layers.17.self_attn.dense.weight": "model-00007-of-00018.safetensors", "model.layers.17.self_attn.query_key_value.bias": "model-00007-of-00018.safetensors", "model.layers.17.self_attn.query_key_value.weight": "model-00007-of-00018.safetensors", "model.layers.18.input_layernorm.bias": "model-00007-of-00018.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00018.safetensors", "model.layers.18.mlp.down_proj.bias": "model-00007-of-00018.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00018.safetensors", "model.layers.18.mlp.up_proj.bias": "model-00007-of-00018.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.18.post_attention_layernorm.bias": "model-00008-of-00018.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.18.self_attn.dense.bias": "model-00008-of-00018.safetensors", "model.layers.18.self_attn.dense.weight": "model-00008-of-00018.safetensors", "model.layers.18.self_attn.query_key_value.bias": "model-00008-of-00018.safetensors", "model.layers.18.self_attn.query_key_value.weight": "model-00008-of-00018.safetensors", "model.layers.19.input_layernorm.bias": "model-00008-of-00018.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.19.mlp.down_proj.bias": "model-00008-of-00018.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.19.mlp.up_proj.bias": "model-00008-of-00018.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00018.safetensors", "model.layers.19.post_attention_layernorm.bias": "model-00008-of-00018.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.19.self_attn.dense.bias": "model-00008-of-00018.safetensors", "model.layers.19.self_attn.dense.weight": "model-00008-of-00018.safetensors", "model.layers.19.self_attn.query_key_value.bias": "model-00008-of-00018.safetensors", "model.layers.19.self_attn.query_key_value.weight": "model-00008-of-00018.safetensors", "model.layers.2.input_layernorm.bias": "model-00008-of-00018.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00018.safetensors", "model.layers.2.mlp.down_proj.bias": "model-00008-of-00018.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00018.safetensors", "model.layers.2.mlp.up_proj.bias": "model-00008-of-00018.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.2.post_attention_layernorm.bias": "model-00009-of-00018.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.2.self_attn.dense.bias": "model-00009-of-00018.safetensors", "model.layers.2.self_attn.dense.weight": "model-00009-of-00018.safetensors", "model.layers.2.self_attn.query_key_value.bias": "model-00009-of-00018.safetensors", "model.layers.2.self_attn.query_key_value.weight": "model-00009-of-00018.safetensors", "model.layers.20.input_layernorm.bias": "model-00009-of-00018.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.20.mlp.down_proj.bias": "model-00009-of-00018.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.20.mlp.up_proj.bias": "model-00009-of-00018.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00018.safetensors", "model.layers.20.post_attention_layernorm.bias": "model-00009-of-00018.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.20.self_attn.dense.bias": "model-00009-of-00018.safetensors", "model.layers.20.self_attn.dense.weight": "model-00009-of-00018.safetensors", "model.layers.20.self_attn.query_key_value.bias": "model-00009-of-00018.safetensors", "model.layers.20.self_attn.query_key_value.weight": "model-00009-of-00018.safetensors", "model.layers.21.input_layernorm.bias": "model-00009-of-00018.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00018.safetensors", "model.layers.21.mlp.down_proj.bias": "model-00009-of-00018.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00018.safetensors", "model.layers.21.mlp.up_proj.bias": "model-00009-of-00018.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.21.post_attention_layernorm.bias": "model-00010-of-00018.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.21.self_attn.dense.bias": "model-00010-of-00018.safetensors", "model.layers.21.self_attn.dense.weight": "model-00010-of-00018.safetensors", "model.layers.21.self_attn.query_key_value.bias": "model-00010-of-00018.safetensors", "model.layers.21.self_attn.query_key_value.weight": "model-00010-of-00018.safetensors", "model.layers.22.input_layernorm.bias": "model-00010-of-00018.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.22.mlp.down_proj.bias": "model-00010-of-00018.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.22.mlp.up_proj.bias": "model-00010-of-00018.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00018.safetensors", "model.layers.22.post_attention_layernorm.bias": "model-00010-of-00018.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.22.self_attn.dense.bias": "model-00010-of-00018.safetensors", "model.layers.22.self_attn.dense.weight": "model-00010-of-00018.safetensors", "model.layers.22.self_attn.query_key_value.bias": "model-00010-of-00018.safetensors", "model.layers.22.self_attn.query_key_value.weight": "model-00010-of-00018.safetensors", "model.layers.23.input_layernorm.bias": "model-00010-of-00018.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00018.safetensors", "model.layers.23.mlp.down_proj.bias": "model-00010-of-00018.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00018.safetensors", "model.layers.23.mlp.up_proj.bias": "model-00010-of-00018.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.23.post_attention_layernorm.bias": "model-00011-of-00018.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.23.self_attn.dense.bias": "model-00011-of-00018.safetensors", "model.layers.23.self_attn.dense.weight": "model-00011-of-00018.safetensors", "model.layers.23.self_attn.query_key_value.bias": "model-00011-of-00018.safetensors", "model.layers.23.self_attn.query_key_value.weight": "model-00011-of-00018.safetensors", "model.layers.24.input_layernorm.bias": "model-00011-of-00018.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.24.mlp.down_proj.bias": "model-00011-of-00018.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.24.mlp.up_proj.bias": "model-00011-of-00018.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00011-of-00018.safetensors", "model.layers.24.post_attention_layernorm.bias": "model-00011-of-00018.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.24.self_attn.dense.bias": "model-00011-of-00018.safetensors", "model.layers.24.self_attn.dense.weight": "model-00011-of-00018.safetensors", "model.layers.24.self_attn.query_key_value.bias": "model-00011-of-00018.safetensors", "model.layers.24.self_attn.query_key_value.weight": "model-00011-of-00018.safetensors", "model.layers.25.input_layernorm.bias": "model-00011-of-00018.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00018.safetensors", "model.layers.25.mlp.down_proj.bias": "model-00011-of-00018.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00018.safetensors", "model.layers.25.mlp.up_proj.bias": "model-00011-of-00018.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.25.post_attention_layernorm.bias": "model-00012-of-00018.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.25.self_attn.dense.bias": "model-00012-of-00018.safetensors", "model.layers.25.self_attn.dense.weight": "model-00012-of-00018.safetensors", "model.layers.25.self_attn.query_key_value.bias": "model-00012-of-00018.safetensors", "model.layers.25.self_attn.query_key_value.weight": "model-00012-of-00018.safetensors", "model.layers.26.input_layernorm.bias": "model-00012-of-00018.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.26.mlp.down_proj.bias": "model-00012-of-00018.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.26.mlp.up_proj.bias": "model-00012-of-00018.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00012-of-00018.safetensors", "model.layers.26.post_attention_layernorm.bias": "model-00012-of-00018.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.26.self_attn.dense.bias": "model-00012-of-00018.safetensors", "model.layers.26.self_attn.dense.weight": "model-00012-of-00018.safetensors", "model.layers.26.self_attn.query_key_value.bias": "model-00012-of-00018.safetensors", "model.layers.26.self_attn.query_key_value.weight": "model-00012-of-00018.safetensors", "model.layers.27.input_layernorm.bias": "model-00012-of-00018.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00018.safetensors", "model.layers.27.mlp.down_proj.bias": "model-00012-of-00018.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00012-of-00018.safetensors", "model.layers.27.mlp.up_proj.bias": "model-00012-of-00018.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.27.post_attention_layernorm.bias": "model-00013-of-00018.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.27.self_attn.dense.bias": "model-00013-of-00018.safetensors", "model.layers.27.self_attn.dense.weight": "model-00013-of-00018.safetensors", "model.layers.27.self_attn.query_key_value.bias": "model-00013-of-00018.safetensors", "model.layers.27.self_attn.query_key_value.weight": "model-00013-of-00018.safetensors", "model.layers.28.input_layernorm.bias": "model-00013-of-00018.safetensors", "model.layers.28.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.28.mlp.down_proj.bias": "model-00013-of-00018.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.28.mlp.up_proj.bias": "model-00013-of-00018.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00018.safetensors", "model.layers.28.post_attention_layernorm.bias": "model-00013-of-00018.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.28.self_attn.dense.bias": "model-00013-of-00018.safetensors", "model.layers.28.self_attn.dense.weight": "model-00013-of-00018.safetensors", "model.layers.28.self_attn.query_key_value.bias": "model-00013-of-00018.safetensors", "model.layers.28.self_attn.query_key_value.weight": "model-00013-of-00018.safetensors", "model.layers.29.input_layernorm.bias": "model-00013-of-00018.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00018.safetensors", "model.layers.29.mlp.down_proj.bias": "model-00013-of-00018.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00018.safetensors", "model.layers.29.mlp.up_proj.bias": "model-00013-of-00018.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.29.post_attention_layernorm.bias": "model-00014-of-00018.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.29.self_attn.dense.bias": "model-00014-of-00018.safetensors", "model.layers.29.self_attn.dense.weight": "model-00014-of-00018.safetensors", "model.layers.29.self_attn.query_key_value.bias": "model-00014-of-00018.safetensors", "model.layers.29.self_attn.query_key_value.weight": "model-00014-of-00018.safetensors", "model.layers.3.input_layernorm.bias": "model-00014-of-00018.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.3.mlp.down_proj.bias": "model-00014-of-00018.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.mlp.up_proj.bias": "model-00014-of-00018.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00018.safetensors", "model.layers.3.post_attention_layernorm.bias": "model-00014-of-00018.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.dense.bias": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.dense.weight": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.query_key_value.bias": "model-00014-of-00018.safetensors", "model.layers.3.self_attn.query_key_value.weight": "model-00014-of-00018.safetensors", "model.layers.30.input_layernorm.bias": "model-00014-of-00018.safetensors", "model.layers.30.input_layernorm.weight": "model-00014-of-00018.safetensors", "model.layers.30.mlp.down_proj.bias": "model-00014-of-00018.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00014-of-00018.safetensors", "model.layers.30.mlp.up_proj.bias": "model-00014-of-00018.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.30.post_attention_layernorm.bias": "model-00015-of-00018.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.30.self_attn.dense.bias": "model-00015-of-00018.safetensors", "model.layers.30.self_attn.dense.weight": "model-00015-of-00018.safetensors", "model.layers.30.self_attn.query_key_value.bias": "model-00015-of-00018.safetensors", "model.layers.30.self_attn.query_key_value.weight": "model-00015-of-00018.safetensors", "model.layers.31.input_layernorm.bias": "model-00015-of-00018.safetensors", "model.layers.31.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.31.mlp.down_proj.bias": "model-00015-of-00018.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.31.mlp.up_proj.bias": "model-00015-of-00018.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00015-of-00018.safetensors", "model.layers.31.post_attention_layernorm.bias": "model-00015-of-00018.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.31.self_attn.dense.bias": "model-00015-of-00018.safetensors", "model.layers.31.self_attn.dense.weight": "model-00015-of-00018.safetensors", "model.layers.31.self_attn.query_key_value.bias": "model-00015-of-00018.safetensors", "model.layers.31.self_attn.query_key_value.weight": "model-00015-of-00018.safetensors", "model.layers.4.input_layernorm.bias": "model-00015-of-00018.safetensors", "model.layers.4.input_layernorm.weight": "model-00015-of-00018.safetensors", "model.layers.4.mlp.down_proj.bias": "model-00015-of-00018.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00015-of-00018.safetensors", "model.layers.4.mlp.up_proj.bias": "model-00015-of-00018.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.4.post_attention_layernorm.bias": "model-00016-of-00018.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.4.self_attn.dense.bias": "model-00016-of-00018.safetensors", "model.layers.4.self_attn.dense.weight": "model-00016-of-00018.safetensors", "model.layers.4.self_attn.query_key_value.bias": "model-00016-of-00018.safetensors", "model.layers.4.self_attn.query_key_value.weight": "model-00016-of-00018.safetensors", "model.layers.5.input_layernorm.bias": "model-00016-of-00018.safetensors", "model.layers.5.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.5.mlp.down_proj.bias": "model-00016-of-00018.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.5.mlp.up_proj.bias": "model-00016-of-00018.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00016-of-00018.safetensors", "model.layers.5.post_attention_layernorm.bias": "model-00016-of-00018.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.5.self_attn.dense.bias": "model-00016-of-00018.safetensors", "model.layers.5.self_attn.dense.weight": "model-00016-of-00018.safetensors", "model.layers.5.self_attn.query_key_value.bias": "model-00016-of-00018.safetensors", "model.layers.5.self_attn.query_key_value.weight": "model-00016-of-00018.safetensors", "model.layers.6.input_layernorm.bias": "model-00016-of-00018.safetensors", "model.layers.6.input_layernorm.weight": "model-00016-of-00018.safetensors", "model.layers.6.mlp.down_proj.bias": "model-00016-of-00018.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00016-of-00018.safetensors", "model.layers.6.mlp.up_proj.bias": "model-00016-of-00018.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.6.post_attention_layernorm.bias": "model-00017-of-00018.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.dense.bias": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.dense.weight": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.query_key_value.bias": "model-00017-of-00018.safetensors", "model.layers.6.self_attn.query_key_value.weight": "model-00017-of-00018.safetensors", "model.layers.7.input_layernorm.bias": "model-00017-of-00018.safetensors", "model.layers.7.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.7.mlp.down_proj.bias": "model-00017-of-00018.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.7.mlp.up_proj.bias": "model-00017-of-00018.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00017-of-00018.safetensors", "model.layers.7.post_attention_layernorm.bias": "model-00017-of-00018.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.dense.bias": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.dense.weight": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.query_key_value.bias": "model-00017-of-00018.safetensors", "model.layers.7.self_attn.query_key_value.weight": "model-00017-of-00018.safetensors", "model.layers.8.input_layernorm.bias": "model-00017-of-00018.safetensors", "model.layers.8.input_layernorm.weight": "model-00017-of-00018.safetensors", "model.layers.8.mlp.down_proj.bias": "model-00017-of-00018.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00017-of-00018.safetensors", "model.layers.8.mlp.up_proj.bias": "model-00017-of-00018.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.8.post_attention_layernorm.bias": "model-00018-of-00018.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.8.self_attn.dense.bias": "model-00018-of-00018.safetensors", "model.layers.8.self_attn.dense.weight": "model-00018-of-00018.safetensors", "model.layers.8.self_attn.query_key_value.bias": "model-00018-of-00018.safetensors", "model.layers.8.self_attn.query_key_value.weight": "model-00018-of-00018.safetensors", "model.layers.9.input_layernorm.bias": "model-00018-of-00018.safetensors", "model.layers.9.input_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.9.mlp.down_proj.bias": "model-00018-of-00018.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.mlp.up_proj.bias": "model-00018-of-00018.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00018-of-00018.safetensors", "model.layers.9.post_attention_layernorm.bias": "model-00018-of-00018.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.dense.bias": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.dense.weight": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.query_key_value.bias": "model-00018-of-00018.safetensors", "model.layers.9.self_attn.query_key_value.weight": "model-00018-of-00018.safetensors"}}
+{
+  "metadata": {
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}