| { |
| "architectures": [ |
| "Qwen4ExpForConditionalGeneration" |
| ], |
| "image_token_id": 248056, |
| "language_model_only": false, |
| "model_type": "qwen4_exp", |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 248044, |
| "dtype": "bfloat16", |
| "eos_token_id": 248044, |
| "full_attention_interval": 4, |
| "hc_count": 4, |
| "hc_lowrank": 320, |
| "head_dim": 256, |
| "heads_per_ngram": 8, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "indexer_budget": 2048, |
| "indexer_compress_ratio": 4, |
| "indexer_head_dim": 128, |
| "indexer_kv_heads": 1, |
| "indexer_n_heads": 4, |
| "initializer_range": 0.02, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention" |
| ], |
| "linear_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 48, |
| "linear_value_head_dim": 128, |
| "make_ngram_vocab_size_divisible_by": 128, |
| "mamba_ssm_dtype": "float32", |
| "max_position_embeddings": 262144, |
| "model_type": "qwen4_exp_text", |
| "moe_intermediate_size": 640, |
| "mtp": { |
| "hybrid": true, |
| "layer_types": [ |
| "full_attention" |
| ], |
| "mtp_use_hidden_state_from_layer": null, |
| "num_hidden_layers": 1, |
| "rope_theta": 10000000 |
| }, |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "ngram_size": 3, |
| "ngram_vocab_size_base": 20000000, |
| "num_attention_heads": 24, |
| "num_experts": 512, |
| "num_experts_per_tok": 10, |
| "num_hidden_layers": 48, |
| "num_key_value_heads": 2, |
| "output_gate_type": "sigmoid", |
| "output_router_logits": false, |
| "pad_token_id": null, |
| "partial_rotary_factor": 0.25, |
| "ple_conv_kernel_size": 4, |
| "ple_embed_dim": 2560, |
| "ple_layer_ids": [ |
| 2 |
| ], |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 10000000, |
| "rope_type": "default" |
| }, |
| "router_aux_loss_coef": 0.001, |
| "shared_expert_intermediate_size": 640, |
| "split_ngram_parts": 128, |
| "tie_word_embeddings": false, |
| "use_cache": true, |
| "vocab_size": 248320 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.8.0.dev0", |
| "video_token_id": 248057, |
| "vision_config": { |
| "deepstack_visual_indexes": [], |
| "depth": 27, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4304, |
| "model_type": "qwen4_exp", |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 2560, |
| "patch_size": 16, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 248054, |
| "vision_start_token_id": 248053, |
| "quantization_config": { |
| "quant_method": "fp8", |
| "activation_scheme": "dynamic", |
| "weight_per_tensor": false, |
| "act_per_tensor": false, |
| "weight_block_size": [ |
| 128, |
| 128 |
| ], |
| "modules_to_not_convert": [ |
| "lm_head", |
| "model.language_model.embed_tokens", |
| "model.language_model.hyper_connection_mixer.input_mix_weight_down", |
| "model.language_model.hyper_connection_mixer.input_mix_weight_up", |
| "model.language_model.layers.0.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.0.linear_attn.conv1d", |
| "model.language_model.layers.0.linear_attn.in_proj_a", |
| "model.language_model.layers.0.linear_attn.in_proj_b", |
| "model.language_model.layers.0.linear_attn.in_proj_qkv", |
| "model.language_model.layers.0.linear_attn.in_proj_z", |
| "model.language_model.layers.0.linear_attn.out_proj", |
| "model.language_model.layers.0.mlp.gate", |
| "model.language_model.layers.0.mlp.shared_expert.down_proj", |
| "model.language_model.layers.0.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.0.mlp.shared_expert.up_proj", |
| "model.language_model.layers.0.mlp.shared_expert_gate", |
| "model.language_model.layers.0.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.1.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.1.linear_attn.conv1d", |
| "model.language_model.layers.1.linear_attn.in_proj_a", |
| "model.language_model.layers.1.linear_attn.in_proj_b", |
| "model.language_model.layers.1.linear_attn.in_proj_qkv", |
| "model.language_model.layers.1.linear_attn.in_proj_z", |
| "model.language_model.layers.1.linear_attn.out_proj", |
| "model.language_model.layers.1.mlp.gate", |
| "model.language_model.layers.1.mlp.shared_expert.down_proj", |
| "model.language_model.layers.1.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.1.mlp.shared_expert.up_proj", |
| "model.language_model.layers.1.mlp.shared_expert_gate", |
| "model.language_model.layers.1.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.1.ple.conv1d", |
| "model.language_model.layers.1.ple.key_proj", |
| "model.language_model.layers.1.ple.value_proj", |
| "model.language_model.layers.10.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.10.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.10.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.10.linear_attn.conv1d", |
| "model.language_model.layers.10.linear_attn.in_proj_a", |
| "model.language_model.layers.10.linear_attn.in_proj_b", |
| "model.language_model.layers.10.linear_attn.in_proj_qkv", |
| "model.language_model.layers.10.linear_attn.in_proj_z", |
| "model.language_model.layers.10.linear_attn.out_proj", |
| "model.language_model.layers.10.mlp.gate", |
| "model.language_model.layers.10.mlp.shared_expert.down_proj", |
| "model.language_model.layers.10.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.10.mlp.shared_expert.up_proj", |
| "model.language_model.layers.10.mlp.shared_expert_gate", |
| "model.language_model.layers.10.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.11.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.11.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.11.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.11.mlp.gate", |
| "model.language_model.layers.11.mlp.shared_expert.down_proj", |
| "model.language_model.layers.11.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.11.mlp.shared_expert.up_proj", |
| "model.language_model.layers.11.mlp.shared_expert_gate", |
| "model.language_model.layers.11.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.11.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.11.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.11.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.11.self_attn.k_proj", |
| "model.language_model.layers.11.self_attn.o_proj", |
| "model.language_model.layers.11.self_attn.q_proj", |
| "model.language_model.layers.11.self_attn.v_proj", |
| "model.language_model.layers.12.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.12.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.12.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.12.linear_attn.conv1d", |
| "model.language_model.layers.12.linear_attn.in_proj_a", |
| "model.language_model.layers.12.linear_attn.in_proj_b", |
| "model.language_model.layers.12.linear_attn.in_proj_qkv", |
| "model.language_model.layers.12.linear_attn.in_proj_z", |
| "model.language_model.layers.12.linear_attn.out_proj", |
| "model.language_model.layers.12.mlp.gate", |
| "model.language_model.layers.12.mlp.shared_expert.down_proj", |
| "model.language_model.layers.12.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.12.mlp.shared_expert.up_proj", |
| "model.language_model.layers.12.mlp.shared_expert_gate", |
| "model.language_model.layers.12.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.12.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.12.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.13.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.13.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.13.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.13.linear_attn.conv1d", |
| "model.language_model.layers.13.linear_attn.in_proj_a", |
| "model.language_model.layers.13.linear_attn.in_proj_b", |
| "model.language_model.layers.13.linear_attn.in_proj_qkv", |
| "model.language_model.layers.13.linear_attn.in_proj_z", |
| "model.language_model.layers.13.linear_attn.out_proj", |
| "model.language_model.layers.13.mlp.gate", |
| "model.language_model.layers.13.mlp.shared_expert.down_proj", |
| "model.language_model.layers.13.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.13.mlp.shared_expert.up_proj", |
| "model.language_model.layers.13.mlp.shared_expert_gate", |
| "model.language_model.layers.13.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.13.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.13.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.14.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.14.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.14.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.14.linear_attn.conv1d", |
| "model.language_model.layers.14.linear_attn.in_proj_a", |
| "model.language_model.layers.14.linear_attn.in_proj_b", |
| "model.language_model.layers.14.linear_attn.in_proj_qkv", |
| "model.language_model.layers.14.linear_attn.in_proj_z", |
| "model.language_model.layers.14.linear_attn.out_proj", |
| "model.language_model.layers.14.mlp.gate", |
| "model.language_model.layers.14.mlp.shared_expert.down_proj", |
| "model.language_model.layers.14.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.14.mlp.shared_expert.up_proj", |
| "model.language_model.layers.14.mlp.shared_expert_gate", |
| "model.language_model.layers.14.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.14.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.14.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.15.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.15.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.15.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.15.mlp.gate", |
| "model.language_model.layers.15.mlp.shared_expert.down_proj", |
| "model.language_model.layers.15.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.15.mlp.shared_expert.up_proj", |
| "model.language_model.layers.15.mlp.shared_expert_gate", |
| "model.language_model.layers.15.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.15.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.15.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.15.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.15.self_attn.k_proj", |
| "model.language_model.layers.15.self_attn.o_proj", |
| "model.language_model.layers.15.self_attn.q_proj", |
| "model.language_model.layers.15.self_attn.v_proj", |
| "model.language_model.layers.16.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.16.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.16.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.16.linear_attn.conv1d", |
| "model.language_model.layers.16.linear_attn.in_proj_a", |
| "model.language_model.layers.16.linear_attn.in_proj_b", |
| "model.language_model.layers.16.linear_attn.in_proj_qkv", |
| "model.language_model.layers.16.linear_attn.in_proj_z", |
| "model.language_model.layers.16.linear_attn.out_proj", |
| "model.language_model.layers.16.mlp.gate", |
| "model.language_model.layers.16.mlp.shared_expert.down_proj", |
| "model.language_model.layers.16.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.16.mlp.shared_expert.up_proj", |
| "model.language_model.layers.16.mlp.shared_expert_gate", |
| "model.language_model.layers.16.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.16.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.16.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.17.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.17.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.17.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.17.linear_attn.conv1d", |
| "model.language_model.layers.17.linear_attn.in_proj_a", |
| "model.language_model.layers.17.linear_attn.in_proj_b", |
| "model.language_model.layers.17.linear_attn.in_proj_qkv", |
| "model.language_model.layers.17.linear_attn.in_proj_z", |
| "model.language_model.layers.17.linear_attn.out_proj", |
| "model.language_model.layers.17.mlp.gate", |
| "model.language_model.layers.17.mlp.shared_expert.down_proj", |
| "model.language_model.layers.17.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.17.mlp.shared_expert.up_proj", |
| "model.language_model.layers.17.mlp.shared_expert_gate", |
| "model.language_model.layers.17.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.17.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.17.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.18.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.18.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.18.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.18.linear_attn.conv1d", |
| "model.language_model.layers.18.linear_attn.in_proj_a", |
| "model.language_model.layers.18.linear_attn.in_proj_b", |
| "model.language_model.layers.18.linear_attn.in_proj_qkv", |
| "model.language_model.layers.18.linear_attn.in_proj_z", |
| "model.language_model.layers.18.linear_attn.out_proj", |
| "model.language_model.layers.18.mlp.gate", |
| "model.language_model.layers.18.mlp.shared_expert.down_proj", |
| "model.language_model.layers.18.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.18.mlp.shared_expert.up_proj", |
| "model.language_model.layers.18.mlp.shared_expert_gate", |
| "model.language_model.layers.18.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.18.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.18.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.19.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.19.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.19.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.19.mlp.gate", |
| "model.language_model.layers.19.mlp.shared_expert.down_proj", |
| "model.language_model.layers.19.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.19.mlp.shared_expert.up_proj", |
| "model.language_model.layers.19.mlp.shared_expert_gate", |
| "model.language_model.layers.19.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.19.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.19.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.19.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.19.self_attn.k_proj", |
| "model.language_model.layers.19.self_attn.o_proj", |
| "model.language_model.layers.19.self_attn.q_proj", |
| "model.language_model.layers.19.self_attn.v_proj", |
| "model.language_model.layers.2.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.2.linear_attn.conv1d", |
| "model.language_model.layers.2.linear_attn.in_proj_a", |
| "model.language_model.layers.2.linear_attn.in_proj_b", |
| "model.language_model.layers.2.linear_attn.in_proj_qkv", |
| "model.language_model.layers.2.linear_attn.in_proj_z", |
| "model.language_model.layers.2.linear_attn.out_proj", |
| "model.language_model.layers.2.mlp.gate", |
| "model.language_model.layers.2.mlp.shared_expert.down_proj", |
| "model.language_model.layers.2.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.2.mlp.shared_expert.up_proj", |
| "model.language_model.layers.2.mlp.shared_expert_gate", |
| "model.language_model.layers.2.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.20.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.20.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.20.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.20.linear_attn.conv1d", |
| "model.language_model.layers.20.linear_attn.in_proj_a", |
| "model.language_model.layers.20.linear_attn.in_proj_b", |
| "model.language_model.layers.20.linear_attn.in_proj_qkv", |
| "model.language_model.layers.20.linear_attn.in_proj_z", |
| "model.language_model.layers.20.linear_attn.out_proj", |
| "model.language_model.layers.20.mlp.gate", |
| "model.language_model.layers.20.mlp.shared_expert.down_proj", |
| "model.language_model.layers.20.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.20.mlp.shared_expert.up_proj", |
| "model.language_model.layers.20.mlp.shared_expert_gate", |
| "model.language_model.layers.20.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.20.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.20.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.21.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.21.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.21.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.21.linear_attn.conv1d", |
| "model.language_model.layers.21.linear_attn.in_proj_a", |
| "model.language_model.layers.21.linear_attn.in_proj_b", |
| "model.language_model.layers.21.linear_attn.in_proj_qkv", |
| "model.language_model.layers.21.linear_attn.in_proj_z", |
| "model.language_model.layers.21.linear_attn.out_proj", |
| "model.language_model.layers.21.mlp.gate", |
| "model.language_model.layers.21.mlp.shared_expert.down_proj", |
| "model.language_model.layers.21.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.21.mlp.shared_expert.up_proj", |
| "model.language_model.layers.21.mlp.shared_expert_gate", |
| "model.language_model.layers.21.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.21.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.21.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.22.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.22.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.22.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.22.linear_attn.conv1d", |
| "model.language_model.layers.22.linear_attn.in_proj_a", |
| "model.language_model.layers.22.linear_attn.in_proj_b", |
| "model.language_model.layers.22.linear_attn.in_proj_qkv", |
| "model.language_model.layers.22.linear_attn.in_proj_z", |
| "model.language_model.layers.22.linear_attn.out_proj", |
| "model.language_model.layers.22.mlp.gate", |
| "model.language_model.layers.22.mlp.shared_expert.down_proj", |
| "model.language_model.layers.22.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.22.mlp.shared_expert.up_proj", |
| "model.language_model.layers.22.mlp.shared_expert_gate", |
| "model.language_model.layers.22.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.22.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.22.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.23.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.23.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.23.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.23.mlp.gate", |
| "model.language_model.layers.23.mlp.shared_expert.down_proj", |
| "model.language_model.layers.23.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.23.mlp.shared_expert.up_proj", |
| "model.language_model.layers.23.mlp.shared_expert_gate", |
| "model.language_model.layers.23.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.23.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.23.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.23.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.23.self_attn.k_proj", |
| "model.language_model.layers.23.self_attn.o_proj", |
| "model.language_model.layers.23.self_attn.q_proj", |
| "model.language_model.layers.23.self_attn.v_proj", |
| "model.language_model.layers.24.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.24.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.24.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.24.linear_attn.conv1d", |
| "model.language_model.layers.24.linear_attn.in_proj_a", |
| "model.language_model.layers.24.linear_attn.in_proj_b", |
| "model.language_model.layers.24.linear_attn.in_proj_qkv", |
| "model.language_model.layers.24.linear_attn.in_proj_z", |
| "model.language_model.layers.24.linear_attn.out_proj", |
| "model.language_model.layers.24.mlp.gate", |
| "model.language_model.layers.24.mlp.shared_expert.down_proj", |
| "model.language_model.layers.24.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.24.mlp.shared_expert.up_proj", |
| "model.language_model.layers.24.mlp.shared_expert_gate", |
| "model.language_model.layers.24.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.24.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.24.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.25.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.25.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.25.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.25.linear_attn.conv1d", |
| "model.language_model.layers.25.linear_attn.in_proj_a", |
| "model.language_model.layers.25.linear_attn.in_proj_b", |
| "model.language_model.layers.25.linear_attn.in_proj_qkv", |
| "model.language_model.layers.25.linear_attn.in_proj_z", |
| "model.language_model.layers.25.linear_attn.out_proj", |
| "model.language_model.layers.25.mlp.gate", |
| "model.language_model.layers.25.mlp.shared_expert.down_proj", |
| "model.language_model.layers.25.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.25.mlp.shared_expert.up_proj", |
| "model.language_model.layers.25.mlp.shared_expert_gate", |
| "model.language_model.layers.25.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.25.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.25.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.26.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.26.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.26.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.26.linear_attn.conv1d", |
| "model.language_model.layers.26.linear_attn.in_proj_a", |
| "model.language_model.layers.26.linear_attn.in_proj_b", |
| "model.language_model.layers.26.linear_attn.in_proj_qkv", |
| "model.language_model.layers.26.linear_attn.in_proj_z", |
| "model.language_model.layers.26.linear_attn.out_proj", |
| "model.language_model.layers.26.mlp.gate", |
| "model.language_model.layers.26.mlp.shared_expert.down_proj", |
| "model.language_model.layers.26.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.26.mlp.shared_expert.up_proj", |
| "model.language_model.layers.26.mlp.shared_expert_gate", |
| "model.language_model.layers.26.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.26.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.26.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.27.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.27.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.27.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.27.mlp.gate", |
| "model.language_model.layers.27.mlp.shared_expert.down_proj", |
| "model.language_model.layers.27.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.27.mlp.shared_expert.up_proj", |
| "model.language_model.layers.27.mlp.shared_expert_gate", |
| "model.language_model.layers.27.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.27.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.27.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.27.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.27.self_attn.k_proj", |
| "model.language_model.layers.27.self_attn.o_proj", |
| "model.language_model.layers.27.self_attn.q_proj", |
| "model.language_model.layers.27.self_attn.v_proj", |
| "model.language_model.layers.28.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.28.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.28.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.28.linear_attn.conv1d", |
| "model.language_model.layers.28.linear_attn.in_proj_a", |
| "model.language_model.layers.28.linear_attn.in_proj_b", |
| "model.language_model.layers.28.linear_attn.in_proj_qkv", |
| "model.language_model.layers.28.linear_attn.in_proj_z", |
| "model.language_model.layers.28.linear_attn.out_proj", |
| "model.language_model.layers.28.mlp.gate", |
| "model.language_model.layers.28.mlp.shared_expert.down_proj", |
| "model.language_model.layers.28.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.28.mlp.shared_expert.up_proj", |
| "model.language_model.layers.28.mlp.shared_expert_gate", |
| "model.language_model.layers.28.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.28.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.28.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.29.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.29.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.29.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.29.linear_attn.conv1d", |
| "model.language_model.layers.29.linear_attn.in_proj_a", |
| "model.language_model.layers.29.linear_attn.in_proj_b", |
| "model.language_model.layers.29.linear_attn.in_proj_qkv", |
| "model.language_model.layers.29.linear_attn.in_proj_z", |
| "model.language_model.layers.29.linear_attn.out_proj", |
| "model.language_model.layers.29.mlp.gate", |
| "model.language_model.layers.29.mlp.shared_expert.down_proj", |
| "model.language_model.layers.29.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.29.mlp.shared_expert.up_proj", |
| "model.language_model.layers.29.mlp.shared_expert_gate", |
| "model.language_model.layers.29.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.29.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.29.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.3.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.3.mlp.gate", |
| "model.language_model.layers.3.mlp.shared_expert.down_proj", |
| "model.language_model.layers.3.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.3.mlp.shared_expert.up_proj", |
| "model.language_model.layers.3.mlp.shared_expert_gate", |
| "model.language_model.layers.3.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.3.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.3.self_attn.k_proj", |
| "model.language_model.layers.3.self_attn.o_proj", |
| "model.language_model.layers.3.self_attn.q_proj", |
| "model.language_model.layers.3.self_attn.v_proj", |
| "model.language_model.layers.30.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.30.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.30.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.30.linear_attn.conv1d", |
| "model.language_model.layers.30.linear_attn.in_proj_a", |
| "model.language_model.layers.30.linear_attn.in_proj_b", |
| "model.language_model.layers.30.linear_attn.in_proj_qkv", |
| "model.language_model.layers.30.linear_attn.in_proj_z", |
| "model.language_model.layers.30.linear_attn.out_proj", |
| "model.language_model.layers.30.mlp.gate", |
| "model.language_model.layers.30.mlp.shared_expert.down_proj", |
| "model.language_model.layers.30.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.30.mlp.shared_expert.up_proj", |
| "model.language_model.layers.30.mlp.shared_expert_gate", |
| "model.language_model.layers.30.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.30.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.30.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.31.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.31.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.31.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.31.mlp.gate", |
| "model.language_model.layers.31.mlp.shared_expert.down_proj", |
| "model.language_model.layers.31.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.31.mlp.shared_expert.up_proj", |
| "model.language_model.layers.31.mlp.shared_expert_gate", |
| "model.language_model.layers.31.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.31.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.31.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.31.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.31.self_attn.k_proj", |
| "model.language_model.layers.31.self_attn.o_proj", |
| "model.language_model.layers.31.self_attn.q_proj", |
| "model.language_model.layers.31.self_attn.v_proj", |
| "model.language_model.layers.32.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.32.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.32.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.32.linear_attn.conv1d", |
| "model.language_model.layers.32.linear_attn.in_proj_a", |
| "model.language_model.layers.32.linear_attn.in_proj_b", |
| "model.language_model.layers.32.linear_attn.in_proj_qkv", |
| "model.language_model.layers.32.linear_attn.in_proj_z", |
| "model.language_model.layers.32.linear_attn.out_proj", |
| "model.language_model.layers.32.mlp.gate", |
| "model.language_model.layers.32.mlp.shared_expert.down_proj", |
| "model.language_model.layers.32.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.32.mlp.shared_expert.up_proj", |
| "model.language_model.layers.32.mlp.shared_expert_gate", |
| "model.language_model.layers.32.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.32.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.32.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.33.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.33.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.33.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.33.linear_attn.conv1d", |
| "model.language_model.layers.33.linear_attn.in_proj_a", |
| "model.language_model.layers.33.linear_attn.in_proj_b", |
| "model.language_model.layers.33.linear_attn.in_proj_qkv", |
| "model.language_model.layers.33.linear_attn.in_proj_z", |
| "model.language_model.layers.33.linear_attn.out_proj", |
| "model.language_model.layers.33.mlp.gate", |
| "model.language_model.layers.33.mlp.shared_expert.down_proj", |
| "model.language_model.layers.33.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.33.mlp.shared_expert.up_proj", |
| "model.language_model.layers.33.mlp.shared_expert_gate", |
| "model.language_model.layers.33.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.33.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.33.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.34.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.34.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.34.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.34.linear_attn.conv1d", |
| "model.language_model.layers.34.linear_attn.in_proj_a", |
| "model.language_model.layers.34.linear_attn.in_proj_b", |
| "model.language_model.layers.34.linear_attn.in_proj_qkv", |
| "model.language_model.layers.34.linear_attn.in_proj_z", |
| "model.language_model.layers.34.linear_attn.out_proj", |
| "model.language_model.layers.34.mlp.gate", |
| "model.language_model.layers.34.mlp.shared_expert.down_proj", |
| "model.language_model.layers.34.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.34.mlp.shared_expert.up_proj", |
| "model.language_model.layers.34.mlp.shared_expert_gate", |
| "model.language_model.layers.34.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.34.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.34.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.35.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.35.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.35.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.35.mlp.gate", |
| "model.language_model.layers.35.mlp.shared_expert.down_proj", |
| "model.language_model.layers.35.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.35.mlp.shared_expert.up_proj", |
| "model.language_model.layers.35.mlp.shared_expert_gate", |
| "model.language_model.layers.35.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.35.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.35.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.35.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.35.self_attn.k_proj", |
| "model.language_model.layers.35.self_attn.o_proj", |
| "model.language_model.layers.35.self_attn.q_proj", |
| "model.language_model.layers.35.self_attn.v_proj", |
| "model.language_model.layers.36.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.36.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.36.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.36.linear_attn.conv1d", |
| "model.language_model.layers.36.linear_attn.in_proj_a", |
| "model.language_model.layers.36.linear_attn.in_proj_b", |
| "model.language_model.layers.36.linear_attn.in_proj_qkv", |
| "model.language_model.layers.36.linear_attn.in_proj_z", |
| "model.language_model.layers.36.linear_attn.out_proj", |
| "model.language_model.layers.36.mlp.gate", |
| "model.language_model.layers.36.mlp.shared_expert.down_proj", |
| "model.language_model.layers.36.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.36.mlp.shared_expert.up_proj", |
| "model.language_model.layers.36.mlp.shared_expert_gate", |
| "model.language_model.layers.36.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.36.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.36.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.37.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.37.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.37.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.37.linear_attn.conv1d", |
| "model.language_model.layers.37.linear_attn.in_proj_a", |
| "model.language_model.layers.37.linear_attn.in_proj_b", |
| "model.language_model.layers.37.linear_attn.in_proj_qkv", |
| "model.language_model.layers.37.linear_attn.in_proj_z", |
| "model.language_model.layers.37.linear_attn.out_proj", |
| "model.language_model.layers.37.mlp.gate", |
| "model.language_model.layers.37.mlp.shared_expert.down_proj", |
| "model.language_model.layers.37.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.37.mlp.shared_expert.up_proj", |
| "model.language_model.layers.37.mlp.shared_expert_gate", |
| "model.language_model.layers.37.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.37.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.37.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.38.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.38.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.38.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.38.linear_attn.conv1d", |
| "model.language_model.layers.38.linear_attn.in_proj_a", |
| "model.language_model.layers.38.linear_attn.in_proj_b", |
| "model.language_model.layers.38.linear_attn.in_proj_qkv", |
| "model.language_model.layers.38.linear_attn.in_proj_z", |
| "model.language_model.layers.38.linear_attn.out_proj", |
| "model.language_model.layers.38.mlp.gate", |
| "model.language_model.layers.38.mlp.shared_expert.down_proj", |
| "model.language_model.layers.38.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.38.mlp.shared_expert.up_proj", |
| "model.language_model.layers.38.mlp.shared_expert_gate", |
| "model.language_model.layers.38.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.38.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.38.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.39.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.39.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.39.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.39.mlp.gate", |
| "model.language_model.layers.39.mlp.shared_expert.down_proj", |
| "model.language_model.layers.39.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.39.mlp.shared_expert.up_proj", |
| "model.language_model.layers.39.mlp.shared_expert_gate", |
| "model.language_model.layers.39.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.39.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.39.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.39.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.39.self_attn.k_proj", |
| "model.language_model.layers.39.self_attn.o_proj", |
| "model.language_model.layers.39.self_attn.q_proj", |
| "model.language_model.layers.39.self_attn.v_proj", |
| "model.language_model.layers.4.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.4.linear_attn.conv1d", |
| "model.language_model.layers.4.linear_attn.in_proj_a", |
| "model.language_model.layers.4.linear_attn.in_proj_b", |
| "model.language_model.layers.4.linear_attn.in_proj_qkv", |
| "model.language_model.layers.4.linear_attn.in_proj_z", |
| "model.language_model.layers.4.linear_attn.out_proj", |
| "model.language_model.layers.4.mlp.gate", |
| "model.language_model.layers.4.mlp.shared_expert.down_proj", |
| "model.language_model.layers.4.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.4.mlp.shared_expert.up_proj", |
| "model.language_model.layers.4.mlp.shared_expert_gate", |
| "model.language_model.layers.4.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.40.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.40.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.40.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.40.linear_attn.conv1d", |
| "model.language_model.layers.40.linear_attn.in_proj_a", |
| "model.language_model.layers.40.linear_attn.in_proj_b", |
| "model.language_model.layers.40.linear_attn.in_proj_qkv", |
| "model.language_model.layers.40.linear_attn.in_proj_z", |
| "model.language_model.layers.40.linear_attn.out_proj", |
| "model.language_model.layers.40.mlp.gate", |
| "model.language_model.layers.40.mlp.shared_expert.down_proj", |
| "model.language_model.layers.40.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.40.mlp.shared_expert.up_proj", |
| "model.language_model.layers.40.mlp.shared_expert_gate", |
| "model.language_model.layers.40.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.40.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.40.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.41.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.41.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.41.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.41.linear_attn.conv1d", |
| "model.language_model.layers.41.linear_attn.in_proj_a", |
| "model.language_model.layers.41.linear_attn.in_proj_b", |
| "model.language_model.layers.41.linear_attn.in_proj_qkv", |
| "model.language_model.layers.41.linear_attn.in_proj_z", |
| "model.language_model.layers.41.linear_attn.out_proj", |
| "model.language_model.layers.41.mlp.gate", |
| "model.language_model.layers.41.mlp.shared_expert.down_proj", |
| "model.language_model.layers.41.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.41.mlp.shared_expert.up_proj", |
| "model.language_model.layers.41.mlp.shared_expert_gate", |
| "model.language_model.layers.41.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.41.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.41.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.42.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.42.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.42.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.42.linear_attn.conv1d", |
| "model.language_model.layers.42.linear_attn.in_proj_a", |
| "model.language_model.layers.42.linear_attn.in_proj_b", |
| "model.language_model.layers.42.linear_attn.in_proj_qkv", |
| "model.language_model.layers.42.linear_attn.in_proj_z", |
| "model.language_model.layers.42.linear_attn.out_proj", |
| "model.language_model.layers.42.mlp.gate", |
| "model.language_model.layers.42.mlp.shared_expert.down_proj", |
| "model.language_model.layers.42.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.42.mlp.shared_expert.up_proj", |
| "model.language_model.layers.42.mlp.shared_expert_gate", |
| "model.language_model.layers.42.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.42.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.42.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.43.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.43.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.43.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.43.mlp.gate", |
| "model.language_model.layers.43.mlp.shared_expert.down_proj", |
| "model.language_model.layers.43.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.43.mlp.shared_expert.up_proj", |
| "model.language_model.layers.43.mlp.shared_expert_gate", |
| "model.language_model.layers.43.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.43.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.43.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.43.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.43.self_attn.k_proj", |
| "model.language_model.layers.43.self_attn.o_proj", |
| "model.language_model.layers.43.self_attn.q_proj", |
| "model.language_model.layers.43.self_attn.v_proj", |
| "model.language_model.layers.44.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.44.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.44.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.44.linear_attn.conv1d", |
| "model.language_model.layers.44.linear_attn.in_proj_a", |
| "model.language_model.layers.44.linear_attn.in_proj_b", |
| "model.language_model.layers.44.linear_attn.in_proj_qkv", |
| "model.language_model.layers.44.linear_attn.in_proj_z", |
| "model.language_model.layers.44.linear_attn.out_proj", |
| "model.language_model.layers.44.mlp.gate", |
| "model.language_model.layers.44.mlp.shared_expert.down_proj", |
| "model.language_model.layers.44.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.44.mlp.shared_expert.up_proj", |
| "model.language_model.layers.44.mlp.shared_expert_gate", |
| "model.language_model.layers.44.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.44.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.44.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.45.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.45.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.45.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.45.linear_attn.conv1d", |
| "model.language_model.layers.45.linear_attn.in_proj_a", |
| "model.language_model.layers.45.linear_attn.in_proj_b", |
| "model.language_model.layers.45.linear_attn.in_proj_qkv", |
| "model.language_model.layers.45.linear_attn.in_proj_z", |
| "model.language_model.layers.45.linear_attn.out_proj", |
| "model.language_model.layers.45.mlp.gate", |
| "model.language_model.layers.45.mlp.shared_expert.down_proj", |
| "model.language_model.layers.45.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.45.mlp.shared_expert.up_proj", |
| "model.language_model.layers.45.mlp.shared_expert_gate", |
| "model.language_model.layers.45.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.45.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.45.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.46.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.46.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.46.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.46.linear_attn.conv1d", |
| "model.language_model.layers.46.linear_attn.in_proj_a", |
| "model.language_model.layers.46.linear_attn.in_proj_b", |
| "model.language_model.layers.46.linear_attn.in_proj_qkv", |
| "model.language_model.layers.46.linear_attn.in_proj_z", |
| "model.language_model.layers.46.linear_attn.out_proj", |
| "model.language_model.layers.46.mlp.gate", |
| "model.language_model.layers.46.mlp.shared_expert.down_proj", |
| "model.language_model.layers.46.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.46.mlp.shared_expert.up_proj", |
| "model.language_model.layers.46.mlp.shared_expert_gate", |
| "model.language_model.layers.46.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.46.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.46.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.47.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.47.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.47.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.47.mlp.gate", |
| "model.language_model.layers.47.mlp.shared_expert.down_proj", |
| "model.language_model.layers.47.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.47.mlp.shared_expert.up_proj", |
| "model.language_model.layers.47.mlp.shared_expert_gate", |
| "model.language_model.layers.47.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.47.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.47.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.47.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.47.self_attn.k_proj", |
| "model.language_model.layers.47.self_attn.o_proj", |
| "model.language_model.layers.47.self_attn.q_proj", |
| "model.language_model.layers.47.self_attn.v_proj", |
| "model.language_model.layers.5.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.5.linear_attn.conv1d", |
| "model.language_model.layers.5.linear_attn.in_proj_a", |
| "model.language_model.layers.5.linear_attn.in_proj_b", |
| "model.language_model.layers.5.linear_attn.in_proj_qkv", |
| "model.language_model.layers.5.linear_attn.in_proj_z", |
| "model.language_model.layers.5.linear_attn.out_proj", |
| "model.language_model.layers.5.mlp.gate", |
| "model.language_model.layers.5.mlp.shared_expert.down_proj", |
| "model.language_model.layers.5.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.5.mlp.shared_expert.up_proj", |
| "model.language_model.layers.5.mlp.shared_expert_gate", |
| "model.language_model.layers.5.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.6.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.6.linear_attn.conv1d", |
| "model.language_model.layers.6.linear_attn.in_proj_a", |
| "model.language_model.layers.6.linear_attn.in_proj_b", |
| "model.language_model.layers.6.linear_attn.in_proj_qkv", |
| "model.language_model.layers.6.linear_attn.in_proj_z", |
| "model.language_model.layers.6.linear_attn.out_proj", |
| "model.language_model.layers.6.mlp.gate", |
| "model.language_model.layers.6.mlp.shared_expert.down_proj", |
| "model.language_model.layers.6.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.6.mlp.shared_expert.up_proj", |
| "model.language_model.layers.6.mlp.shared_expert_gate", |
| "model.language_model.layers.6.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.7.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.7.mlp.gate", |
| "model.language_model.layers.7.mlp.shared_expert.down_proj", |
| "model.language_model.layers.7.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.7.mlp.shared_expert.up_proj", |
| "model.language_model.layers.7.mlp.shared_expert_gate", |
| "model.language_model.layers.7.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.7.self_attn.indexer.index_qk_proj", |
| "model.language_model.layers.7.self_attn.k_proj", |
| "model.language_model.layers.7.self_attn.o_proj", |
| "model.language_model.layers.7.self_attn.q_proj", |
| "model.language_model.layers.7.self_attn.v_proj", |
| "model.language_model.layers.8.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.8.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.8.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.8.linear_attn.conv1d", |
| "model.language_model.layers.8.linear_attn.in_proj_a", |
| "model.language_model.layers.8.linear_attn.in_proj_b", |
| "model.language_model.layers.8.linear_attn.in_proj_qkv", |
| "model.language_model.layers.8.linear_attn.in_proj_z", |
| "model.language_model.layers.8.linear_attn.out_proj", |
| "model.language_model.layers.8.mlp.gate", |
| "model.language_model.layers.8.mlp.shared_expert.down_proj", |
| "model.language_model.layers.8.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.8.mlp.shared_expert.up_proj", |
| "model.language_model.layers.8.mlp.shared_expert_gate", |
| "model.language_model.layers.8.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.9.attn_hyper_connection.block_inject_weight", |
| "model.language_model.layers.9.attn_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.9.attn_hyper_connection.input_mix_weight_up", |
| "model.language_model.layers.9.linear_attn.conv1d", |
| "model.language_model.layers.9.linear_attn.in_proj_a", |
| "model.language_model.layers.9.linear_attn.in_proj_b", |
| "model.language_model.layers.9.linear_attn.in_proj_qkv", |
| "model.language_model.layers.9.linear_attn.in_proj_z", |
| "model.language_model.layers.9.linear_attn.out_proj", |
| "model.language_model.layers.9.mlp.gate", |
| "model.language_model.layers.9.mlp.shared_expert.down_proj", |
| "model.language_model.layers.9.mlp.shared_expert.gate_proj", |
| "model.language_model.layers.9.mlp.shared_expert.up_proj", |
| "model.language_model.layers.9.mlp.shared_expert_gate", |
| "model.language_model.layers.9.mlp_hyper_connection.block_inject_weight", |
| "model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_down", |
| "model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_up", |
| "model.visual.blocks.0.attn.proj", |
| "model.visual.blocks.0.attn.qkv", |
| "model.visual.blocks.0.mlp.linear_fc1", |
| "model.visual.blocks.0.mlp.linear_fc2", |
| "model.visual.blocks.1.attn.proj", |
| "model.visual.blocks.1.attn.qkv", |
| "model.visual.blocks.1.mlp.linear_fc1", |
| "model.visual.blocks.1.mlp.linear_fc2", |
| "model.visual.blocks.10.attn.proj", |
| "model.visual.blocks.10.attn.qkv", |
| "model.visual.blocks.10.mlp.linear_fc1", |
| "model.visual.blocks.10.mlp.linear_fc2", |
| "model.visual.blocks.11.attn.proj", |
| "model.visual.blocks.11.attn.qkv", |
| "model.visual.blocks.11.mlp.linear_fc1", |
| "model.visual.blocks.11.mlp.linear_fc2", |
| "model.visual.blocks.12.attn.proj", |
| "model.visual.blocks.12.attn.qkv", |
| "model.visual.blocks.12.mlp.linear_fc1", |
| "model.visual.blocks.12.mlp.linear_fc2", |
| "model.visual.blocks.13.attn.proj", |
| "model.visual.blocks.13.attn.qkv", |
| "model.visual.blocks.13.mlp.linear_fc1", |
| "model.visual.blocks.13.mlp.linear_fc2", |
| "model.visual.blocks.14.attn.proj", |
| "model.visual.blocks.14.attn.qkv", |
| "model.visual.blocks.14.mlp.linear_fc1", |
| "model.visual.blocks.14.mlp.linear_fc2", |
| "model.visual.blocks.15.attn.proj", |
| "model.visual.blocks.15.attn.qkv", |
| "model.visual.blocks.15.mlp.linear_fc1", |
| "model.visual.blocks.15.mlp.linear_fc2", |
| "model.visual.blocks.16.attn.proj", |
| "model.visual.blocks.16.attn.qkv", |
| "model.visual.blocks.16.mlp.linear_fc1", |
| "model.visual.blocks.16.mlp.linear_fc2", |
| "model.visual.blocks.17.attn.proj", |
| "model.visual.blocks.17.attn.qkv", |
| "model.visual.blocks.17.mlp.linear_fc1", |
| "model.visual.blocks.17.mlp.linear_fc2", |
| "model.visual.blocks.18.attn.proj", |
| "model.visual.blocks.18.attn.qkv", |
| "model.visual.blocks.18.mlp.linear_fc1", |
| "model.visual.blocks.18.mlp.linear_fc2", |
| "model.visual.blocks.19.attn.proj", |
| "model.visual.blocks.19.attn.qkv", |
| "model.visual.blocks.19.mlp.linear_fc1", |
| "model.visual.blocks.19.mlp.linear_fc2", |
| "model.visual.blocks.2.attn.proj", |
| "model.visual.blocks.2.attn.qkv", |
| "model.visual.blocks.2.mlp.linear_fc1", |
| "model.visual.blocks.2.mlp.linear_fc2", |
| "model.visual.blocks.20.attn.proj", |
| "model.visual.blocks.20.attn.qkv", |
| "model.visual.blocks.20.mlp.linear_fc1", |
| "model.visual.blocks.20.mlp.linear_fc2", |
| "model.visual.blocks.21.attn.proj", |
| "model.visual.blocks.21.attn.qkv", |
| "model.visual.blocks.21.mlp.linear_fc1", |
| "model.visual.blocks.21.mlp.linear_fc2", |
| "model.visual.blocks.22.attn.proj", |
| "model.visual.blocks.22.attn.qkv", |
| "model.visual.blocks.22.mlp.linear_fc1", |
| "model.visual.blocks.22.mlp.linear_fc2", |
| "model.visual.blocks.23.attn.proj", |
| "model.visual.blocks.23.attn.qkv", |
| "model.visual.blocks.23.mlp.linear_fc1", |
| "model.visual.blocks.23.mlp.linear_fc2", |
| "model.visual.blocks.24.attn.proj", |
| "model.visual.blocks.24.attn.qkv", |
| "model.visual.blocks.24.mlp.linear_fc1", |
| "model.visual.blocks.24.mlp.linear_fc2", |
| "model.visual.blocks.25.attn.proj", |
| "model.visual.blocks.25.attn.qkv", |
| "model.visual.blocks.25.mlp.linear_fc1", |
| "model.visual.blocks.25.mlp.linear_fc2", |
| "model.visual.blocks.26.attn.proj", |
| "model.visual.blocks.26.attn.qkv", |
| "model.visual.blocks.26.mlp.linear_fc1", |
| "model.visual.blocks.26.mlp.linear_fc2", |
| "model.visual.blocks.3.attn.proj", |
| "model.visual.blocks.3.attn.qkv", |
| "model.visual.blocks.3.mlp.linear_fc1", |
| "model.visual.blocks.3.mlp.linear_fc2", |
| "model.visual.blocks.4.attn.proj", |
| "model.visual.blocks.4.attn.qkv", |
| "model.visual.blocks.4.mlp.linear_fc1", |
| "model.visual.blocks.4.mlp.linear_fc2", |
| "model.visual.blocks.5.attn.proj", |
| "model.visual.blocks.5.attn.qkv", |
| "model.visual.blocks.5.mlp.linear_fc1", |
| "model.visual.blocks.5.mlp.linear_fc2", |
| "model.visual.blocks.6.attn.proj", |
| "model.visual.blocks.6.attn.qkv", |
| "model.visual.blocks.6.mlp.linear_fc1", |
| "model.visual.blocks.6.mlp.linear_fc2", |
| "model.visual.blocks.7.attn.proj", |
| "model.visual.blocks.7.attn.qkv", |
| "model.visual.blocks.7.mlp.linear_fc1", |
| "model.visual.blocks.7.mlp.linear_fc2", |
| "model.visual.blocks.8.attn.proj", |
| "model.visual.blocks.8.attn.qkv", |
| "model.visual.blocks.8.mlp.linear_fc1", |
| "model.visual.blocks.8.mlp.linear_fc2", |
| "model.visual.blocks.9.attn.proj", |
| "model.visual.blocks.9.attn.qkv", |
| "model.visual.blocks.9.mlp.linear_fc1", |
| "model.visual.blocks.9.mlp.linear_fc2", |
| "model.visual.merger.linear_fc1", |
| "model.visual.merger.linear_fc2", |
| "model.visual.patch_embed.proj", |
| "model.visual.pos_embed", |
| "mtp.fc_embedding", |
| "mtp.fc_hidden", |
| "mtp.hyper_connection_mixer.input_mix_weight_down", |
| "mtp.hyper_connection_mixer.input_mix_weight_up", |
| "mtp.layers.0.attn_hyper_connection.block_inject_weight", |
| "mtp.layers.0.attn_hyper_connection.input_mix_weight_down", |
| "mtp.layers.0.attn_hyper_connection.input_mix_weight_up", |
| "mtp.layers.0.mlp.gate", |
| "mtp.layers.0.mlp.shared_expert.down_proj", |
| "mtp.layers.0.mlp.shared_expert.gate_proj", |
| "mtp.layers.0.mlp.shared_expert.up_proj", |
| "mtp.layers.0.mlp.shared_expert_gate", |
| "mtp.layers.0.mlp_hyper_connection.block_inject_weight", |
| "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down", |
| "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up", |
| "mtp.layers.0.self_attn.indexer.index_qk_proj", |
| "mtp.layers.0.self_attn.k_proj", |
| "mtp.layers.0.self_attn.o_proj", |
| "mtp.layers.0.self_attn.q_proj", |
| "mtp.layers.0.self_attn.v_proj" |
| ] |
| } |
| } |
