{ "architectures": [ "Glm4vMoeForConditionalGeneration" ], "model_type": "glm4v_moe", "image_start_token_id": 151339, "image_end_token_id": 151340, "video_start_token_id": 151341, "video_end_token_id": 151342, "image_token_id": 151363, "video_token_id": 151364, "tie_word_embeddings": false, "transformers_version": "4.57.1", "text_config": { "model_type": "glm4v_moe_text", "pad_token_id": 151329, "vocab_size": 151552, "eos_token_id": [ 151329, 151336, 151338 ], "head_dim": 128, "attention_bias": true, "attention_dropout": 0.0, "first_k_dense_replace": 1, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 10944, "max_position_embeddings": 65536, "moe_intermediate_size": 1408, "n_group": 1, "n_routed_experts": 128, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 96, "num_experts_per_tok": 8, "num_hidden_layers": 46, "num_key_value_heads": 8, "partial_rotary_factor": 0.5, "rms_norm_eps": 1e-05, "dtype": "bfloat16", "rope_scaling": { "rope_type": "default", "mrope_section": [ 8, 12, 12 ] }, "rope_theta": 10000.0, "routed_scaling_factor": 1.0, "topk_group": 1, "use_cache": true, "use_qk_norm": false }, "vision_config": { "attention_bias": false, "attention_dropout": 0.0, "depth": 24, "hidden_act": "silu", "hidden_size": 1536, "image_size": 336, "in_channels": 3, "initializer_range": 0.02, "intermediate_size": 10944, "model_type": "glm4v_moe", "num_heads": 12, "out_hidden_size": 4096, "patch_size": 14, "rms_norm_eps": 1e-05, "spatial_merge_size": 2, "temporal_patch_size": 2 }, "quantization_config": { "config_groups": { "group_0": { "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": null, "observer_kwargs": {}, "strategy": "token", "symmetric": true, "type": "float" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "strategy": "channel", "symmetric": true, "type": "float" } } }, "format": "float-quantized", "ignore": [ "model.layers.4.input_layernorm", "model.layers.3.input_layernorm", "model.layers.2.input_layernorm", "model.layers.0.input_layernorm", "model.layers.1.input_layernorm", "model.layers.8.input_layernorm", "model.layers.6.input_layernorm", "model.layers.7.input_layernorm", "model.layers.5.input_layernorm", "model.layers.9.input_layernorm", "visual.blocks.6.norm1", "visual.blocks.7.norm1", "visual.blocks.8.norm1", "visual.blocks.9.norm1", "visual.patch_embed.proj.bias", "visual.downsample.bias", "model.layers.38.mlp.gate", "model.layers.39.mlp.gate", "model.layers.40.mlp.gate", "model.layers.41.mlp.gate", "model.layers.42.mlp.gate", "model.layers.28.mlp.gate", "model.layers.29.mlp.gate", "model.layers.30.mlp.gate", "model.layers.31.mlp.gate", "model.layers.32.mlp.gate", "model.layers.31.self_attn.q_proj.bias", "model.layers.32.self_attn.q_proj.bias", "model.layers.33.self_attn.q_proj.bias", "model.layers.43.self_attn.q_proj.bias", "model.layers.44.self_attn.q_proj.bias", "model.layers.45.self_attn.q_proj.bias", "model.layers.20.self_attn.q_proj.bias", "model.layers.22.self_attn.q_proj.bias", "model.layers.21.self_attn.q_proj.bias", "model.layers.23.self_attn.q_proj.bias", "model.layers.10.self_attn.q_proj.bias", "model.layers.11.self_attn.q_proj.bias", "model.layers.12.self_attn.q_proj.bias", "model.layers.14.self_attn.q_proj.bias", "model.layers.38.self_attn.q_proj.bias", "model.layers.39.self_attn.q_proj.bias", "model.layers.37.post_attention_layernorm", "model.layers.38.post_attention_layernorm", "model.layers.39.post_attention_layernorm", "model.layers.20.post_attention_layernorm", "model.layers.22.post_attention_layernorm", "model.layers.21.post_attention_layernorm", "model.layers.23.post_attention_layernorm", "model.layers.24.post_attention_layernorm", "model.layers.25.post_attention_layernorm", "model.layers.26.post_attention_layernorm", "model.layers.43.self_attn.k_proj.bias", "model.layers.44.self_attn.k_proj.bias", "model.layers.45.self_attn.k_proj.bias", "model.layers.5.self_attn.v_proj.bias", "model.layers.9.self_attn.v_proj.bias", "model.layers.33.mlp.gate", "model.layers.34.mlp.gate", "model.layers.35.mlp.gate", "model.layers.36.mlp.gate", "model.layers.37.mlp.gate", "model.layers.10.mlp.gate", "model.layers.11.mlp.gate", "model.layers.12.mlp.gate", "model.layers.14.mlp.gate", "model.layers.13.mlp.gate", "model.layers.6.mlp.gate", "model.layers.7.mlp.gate", "model.layers.5.mlp.gate", "model.layers.3.mlp.gate", "model.layers.2.mlp.gate", "model.layers.4.mlp.gate", "model.layers.1.mlp.gate", "model.layers.8.mlp.gate", "model.layers.9.mlp.gate", "visual.blocks.15.mlp.gate_up_proj", "visual.blocks.15.mlp.gate_proj", "visual.blocks.15.mlp.up_proj", "visual.blocks.16.mlp.down_proj", "visual.blocks.16.mlp.gate_up_proj", "visual.blocks.16.mlp.gate_proj", "visual.blocks.16.mlp.up_proj", "visual.blocks.17.mlp.down_proj", "visual.blocks.17.mlp.gate_up_proj", "visual.blocks.17.mlp.gate_proj", "visual.blocks.17.mlp.up_proj", "visual.blocks.18.mlp.down_proj", "visual.blocks.18.mlp.gate_up_proj", "visual.blocks.18.mlp.gate_proj", "visual.blocks.18.mlp.up_proj", "visual.blocks.19.mlp.down_proj", "visual.blocks.19.mlp.gate_up_proj", "visual.blocks.19.mlp.gate_proj", "visual.blocks.19.mlp.up_proj", "visual.blocks.20.mlp.down_proj", "visual.post_layernorm", "model.layers.40.mlp.gate.e_score_correction_bias", "model.layers.41.mlp.gate.e_score_correction_bias", "model.layers.42.mlp.gate.e_score_correction_bias", "model.layers.29.mlp.gate.e_score_correction_bias", "model.layers.30.mlp.gate.e_score_correction_bias", "model.layers.31.mlp.gate.e_score_correction_bias", "model.layers.32.mlp.gate.e_score_correction_bias", "model.layers.33.mlp.gate.e_score_correction_bias", "model.layers.34.mlp.gate.e_score_correction_bias", "model.layers.35.mlp.gate.e_score_correction_bias", "visual.blocks.12.norm1", "visual.blocks.12.norm2", "visual.blocks.13.norm1", "visual.blocks.13.norm2", "visual.blocks.14.norm1", "visual.blocks.14.norm2", "visual.blocks.15.norm1", "visual.blocks.15.norm2", "visual.blocks.16.norm2", "visual.blocks.17.norm2", "model.layers.45.mlp.gate.e_score_correction_bias", "model.layers.17.post_attention_layernorm", "model.layers.18.post_attention_layernorm", "model.layers.19.post_attention_layernorm", "model.layers.43.post_attention_layernorm", "model.layers.44.post_attention_layernorm", "model.layers.45.post_attention_layernorm", "model.layers.20.self_attn.v_proj.bias", "model.layers.22.self_attn.v_proj.bias", "model.layers.21.self_attn.v_proj.bias", "model.layers.23.self_attn.v_proj.bias", "model.layers.24.self_attn.v_proj.bias", "model.layers.25.self_attn.v_proj.bias", "model.layers.26.self_attn.v_proj.bias", "model.layers.27.self_attn.v_proj.bias", "model.layers.28.self_attn.v_proj.bias", "model.layers.29.self_attn.v_proj.bias", "visual.blocks.11.mlp.gate_up_proj", "visual.blocks.11.mlp.gate_proj", "visual.blocks.11.mlp.up_proj", "visual.blocks.5.mlp.gate_up_proj", "visual.blocks.5.mlp.gate_proj", "visual.blocks.5.mlp.up_proj", "visual.blocks.5.norm1", "visual.blocks.6.mlp.gate_up_proj", "visual.blocks.6.mlp.gate_proj", "visual.blocks.6.mlp.up_proj", "visual.blocks.7.mlp.gate_up_proj", "visual.blocks.7.mlp.gate_proj", "visual.blocks.7.mlp.up_proj", "visual.blocks.8.mlp.gate_up_proj", "visual.blocks.8.mlp.gate_proj", "visual.blocks.8.mlp.up_proj", "visual.blocks.9.mlp.gate_up_proj", "visual.blocks.9.mlp.gate_proj", "visual.blocks.9.mlp.up_proj", "model.layers.22.mlp.gate.e_score_correction_bias", "model.layers.10.mlp.gate.e_score_correction_bias", "model.layers.11.mlp.gate.e_score_correction_bias", "model.layers.12.mlp.gate.e_score_correction_bias", "visual.blocks.12.mlp.down_proj", "visual.blocks.12.mlp.gate_up_proj", "visual.blocks.12.mlp.gate_proj", "visual.blocks.12.mlp.up_proj", "model.layers.14.mlp.gate.e_score_correction_bias", "model.layers.13.mlp.gate.e_score_correction_bias", "model.layers.15.mlp.gate.e_score_correction_bias", "visual.blocks.13.mlp.down_proj", "visual.blocks.13.mlp.gate_up_proj", "visual.blocks.13.mlp.gate_proj", "visual.blocks.13.mlp.up_proj", "visual.blocks.14.mlp.down_proj", "visual.blocks.14.mlp.gate_up_proj", "visual.blocks.14.mlp.gate_proj", "visual.blocks.14.mlp.up_proj", "visual.blocks.15.mlp.down_proj", "model.embed_tokens", "model.layers.10.input_layernorm", "model.layers.11.input_layernorm", "model.layers.12.input_layernorm", "model.layers.14.input_layernorm", "model.layers.39.input_layernorm", "model.layers.13.input_layernorm", "model.layers.15.input_layernorm", "model.layers.16.input_layernorm", "model.layers.17.input_layernorm", "model.layers.18.input_layernorm", "model.layers.27.post_attention_layernorm", "model.layers.28.post_attention_layernorm", "model.layers.29.post_attention_layernorm", "model.layers.10.post_attention_layernorm", "model.layers.11.post_attention_layernorm", "model.layers.12.post_attention_layernorm", "model.layers.14.post_attention_layernorm", "model.layers.13.post_attention_layernorm", "model.layers.15.post_attention_layernorm", "model.layers.16.post_attention_layernorm", "visual.blocks.19.norm2", "visual.blocks.20.norm2", "visual.blocks.21.norm2", "visual.blocks.22.norm2", "visual.blocks.23.norm2", "visual.blocks.10.norm2", "visual.blocks.11.norm2", "model.layers.2.mlp.gate.e_score_correction_bias", "model.layers.4.mlp.gate.e_score_correction_bias", "model.layers.3.mlp.gate.e_score_correction_bias", "model.layers.1.mlp.gate.e_score_correction_bias", "model.layers.8.mlp.gate.e_score_correction_bias", "model.layers.6.mlp.gate.e_score_correction_bias", "model.layers.7.mlp.gate.e_score_correction_bias", "model.layers.5.mlp.gate.e_score_correction_bias", "model.layers.9.mlp.gate.e_score_correction_bias", "model.layers.2.self_attn.k_proj.bias", "model.layers.4.self_attn.k_proj.bias", "model.layers.3.self_attn.k_proj.bias", "model.layers.0.self_attn.k_proj.bias", "model.layers.1.self_attn.k_proj.bias", "model.layers.8.self_attn.k_proj.bias", "model.layers.6.self_attn.k_proj.bias", "model.layers.7.self_attn.k_proj.bias", "model.layers.5.self_attn.k_proj.bias", "model.layers.9.self_attn.k_proj.bias", "model.layers.34.self_attn.q_proj.bias", "model.layers.35.self_attn.q_proj.bias", "model.layers.36.self_attn.q_proj.bias", "model.layers.37.self_attn.q_proj.bias", "model.layers.13.self_attn.q_proj.bias", "model.layers.15.self_attn.q_proj.bias", "model.layers.16.self_attn.q_proj.bias", "model.layers.17.self_attn.q_proj.bias", "model.layers.18.self_attn.q_proj.bias", "model.layers.19.self_attn.q_proj.bias", "model.layers.40.self_attn.q_proj.bias", "model.layers.41.self_attn.q_proj.bias", "model.layers.42.self_attn.q_proj.bias", "model.layers.24.self_attn.q_proj.bias", "model.layers.25.self_attn.q_proj.bias", "model.layers.26.self_attn.q_proj.bias", "model.layers.27.self_attn.q_proj.bias", "model.layers.28.self_attn.q_proj.bias", "model.layers.29.self_attn.q_proj.bias", "model.layers.30.self_attn.q_proj.bias", "model.layers.25.mlp.gate.e_score_correction_bias", "model.layers.26.mlp.gate.e_score_correction_bias", "model.layers.27.mlp.gate.e_score_correction_bias", "model.layers.28.mlp.gate.e_score_correction_bias", "model.layers.39.mlp.gate.e_score_correction_bias", "model.layers.16.mlp.gate.e_score_correction_bias", "model.layers.17.mlp.gate.e_score_correction_bias", "model.layers.18.mlp.gate.e_score_correction_bias", "model.layers.19.mlp.gate.e_score_correction_bias", "model.layers.20.mlp.gate.e_score_correction_bias", "model.layers.36.mlp.gate.e_score_correction_bias", "model.layers.37.mlp.gate.e_score_correction_bias", "model.layers.38.mlp.gate.e_score_correction_bias", "model.layers.21.mlp.gate.e_score_correction_bias", "model.layers.23.mlp.gate.e_score_correction_bias", "model.layers.24.mlp.gate.e_score_correction_bias", "model.layers.22.self_attn.k_proj.bias", "model.layers.21.self_attn.k_proj.bias", "model.layers.23.self_attn.k_proj.bias", "model.layers.24.self_attn.k_proj.bias", "model.layers.25.self_attn.k_proj.bias", "model.layers.26.self_attn.k_proj.bias", "model.layers.27.self_attn.k_proj.bias", "model.layers.28.self_attn.k_proj.bias", "model.layers.38.self_attn.k_proj.bias", "model.layers.39.self_attn.k_proj.bias", "visual.blocks.0.norm1", "visual.blocks.1.norm1", "visual.blocks.2.norm1", "visual.blocks.0.norm2", "visual.blocks.1.norm2", "visual.blocks.2.norm2", "visual.blocks.3.norm1", "visual.blocks.3.norm2", "visual.blocks.4.norm1", "visual.blocks.19.attn.qkv_proj", "visual.blocks.20.attn.qkv_proj", "visual.blocks.21.attn.qkv_proj", "visual.blocks.22.attn.qkv_proj", "visual.blocks.23.attn.qkv_proj", "visual.blocks.10.attn.qkv_proj", "visual.blocks.11.attn.qkv_proj", "visual.blocks.4.norm2", "visual.blocks.5.norm2", "visual.blocks.6.norm2", "visual.blocks.7.norm2", "visual.blocks.8.norm2", "visual.blocks.9.norm2", "visual.blocks.20.mlp.gate_up_proj", "visual.blocks.20.mlp.gate_proj", "visual.blocks.20.mlp.up_proj", "visual.blocks.21.mlp.down_proj", "visual.blocks.21.mlp.gate_up_proj", "visual.blocks.21.mlp.gate_proj", "visual.blocks.21.mlp.up_proj", "visual.blocks.22.mlp.down_proj", "visual.blocks.22.mlp.gate_up_proj", "visual.blocks.22.mlp.gate_proj", "visual.blocks.22.mlp.up_proj", "visual.blocks.23.mlp.down_proj", "visual.blocks.23.mlp.gate_up_proj", "visual.blocks.23.mlp.gate_proj", "visual.blocks.23.mlp.up_proj", "visual.blocks.10.mlp.down_proj", "visual.blocks.10.mlp.gate_up_proj", "visual.blocks.10.mlp.gate_proj", "visual.blocks.10.mlp.up_proj", "visual.blocks.11.mlp.down_proj", "visual.embeddings.position_embedding", "model.layers.15.mlp.gate", "model.layers.16.mlp.gate", "model.layers.17.mlp.gate", "visual.merger.proj", "model.layers.43.mlp.gate", "model.layers.44.mlp.gate", "model.layers.45.mlp.gate", "model.layers.32.input_layernorm", "model.layers.33.input_layernorm", "model.layers.34.input_layernorm", "model.layers.35.input_layernorm", "model.layers.36.input_layernorm", "model.layers.37.input_layernorm", "model.layers.38.input_layernorm", "model.layers.40.input_layernorm", "model.layers.41.input_layernorm", "model.layers.42.input_layernorm", "model.layers.10.self_attn.k_proj.bias", "model.layers.11.self_attn.k_proj.bias", "model.layers.12.self_attn.k_proj.bias", "model.layers.14.self_attn.k_proj.bias", "model.layers.13.self_attn.k_proj.bias", "model.layers.15.self_attn.k_proj.bias", "model.layers.16.self_attn.k_proj.bias", "model.layers.17.self_attn.k_proj.bias", "model.layers.18.self_attn.k_proj.bias", "model.layers.19.self_attn.k_proj.bias", "visual.patch_embed.proj", "model.layers.32.self_attn.k_proj.bias", "model.layers.33.self_attn.k_proj.bias", "model.layers.34.self_attn.k_proj.bias", "model.layers.35.self_attn.k_proj.bias", "model.layers.36.self_attn.k_proj.bias", "model.layers.37.self_attn.k_proj.bias", "model.layers.40.self_attn.k_proj.bias", "model.layers.41.self_attn.k_proj.bias", "model.layers.42.self_attn.k_proj.bias", "model.layers.29.self_attn.k_proj.bias", "lm_head", "model.layers.40.post_attention_layernorm", "model.layers.41.post_attention_layernorm", "model.layers.42.post_attention_layernorm", "model.layers.30.post_attention_layernorm", "model.layers.31.post_attention_layernorm", "model.layers.32.post_attention_layernorm", "model.layers.33.post_attention_layernorm", "model.layers.34.post_attention_layernorm", "model.layers.35.post_attention_layernorm", "model.layers.36.post_attention_layernorm", "model.layers.30.self_attn.k_proj.bias", "model.layers.31.self_attn.k_proj.bias", "model.layers.20.self_attn.k_proj.bias", "model.layers.21.input_layernorm", "model.layers.23.input_layernorm", "model.layers.24.input_layernorm", "model.layers.25.input_layernorm", "model.layers.26.input_layernorm", "model.layers.27.input_layernorm", "model.layers.28.input_layernorm", "model.layers.29.input_layernorm", "model.layers.30.input_layernorm", "model.layers.31.input_layernorm", "visual.blocks.22.attn.proj", "visual.blocks.23.attn.proj", "visual.blocks.10.attn.proj", "visual.blocks.11.attn.proj", "visual.merger.down_proj", "visual.merger.gate_up_proj", "visual.merger.post_projection_norm.bias", "model.norm", "visual.blocks.16.norm1", "visual.blocks.17.norm1", "visual.blocks.18.norm1", "visual.blocks.19.norm1", "visual.blocks.20.norm1", "visual.blocks.21.norm1", "visual.blocks.22.norm1", "visual.blocks.23.norm1", "visual.blocks.10.norm1", "visual.blocks.11.norm1", "visual.blocks.18.norm2", "model.layers.10.self_attn.v_proj.bias", "model.layers.11.self_attn.v_proj.bias", "model.layers.12.self_attn.v_proj.bias", "model.layers.14.self_attn.v_proj.bias", "model.layers.13.self_attn.v_proj.bias", "model.layers.15.self_attn.v_proj.bias", "model.layers.16.self_attn.v_proj.bias", "model.layers.17.self_attn.v_proj.bias", "model.layers.18.self_attn.v_proj.bias", "model.layers.19.self_attn.v_proj.bias", "visual.blocks.0.attn.qkv_proj", "visual.blocks.1.attn.qkv_proj", "visual.blocks.2.attn.qkv_proj", "visual.blocks.3.attn.qkv_proj", "visual.blocks.4.attn.qkv_proj", "visual.blocks.5.attn.qkv_proj", "visual.blocks.6.attn.qkv_proj", "visual.blocks.7.attn.qkv_proj", "visual.blocks.8.attn.qkv_proj", "visual.blocks.9.attn.qkv_proj", "model.layers.31.self_attn.v_proj.bias", "model.layers.32.self_attn.v_proj.bias", "model.layers.33.self_attn.v_proj.bias", "model.layers.43.self_attn.v_proj.bias", "model.layers.44.self_attn.v_proj.bias", "model.layers.45.self_attn.v_proj.bias", "visual.post_conv_layernorm", "visual.blocks.0.mlp.down_proj", "visual.blocks.0.mlp.gate_up_proj", "visual.blocks.0.mlp.gate_proj", "visual.blocks.0.mlp.up_proj", "visual.blocks.1.mlp.down_proj", "visual.blocks.1.mlp.gate_up_proj", "visual.blocks.1.mlp.gate_proj", "visual.blocks.1.mlp.up_proj", "visual.blocks.2.mlp.down_proj", "visual.blocks.2.mlp.gate_up_proj", "visual.blocks.2.mlp.gate_proj", "visual.blocks.2.mlp.up_proj", "visual.blocks.3.mlp.down_proj", "visual.blocks.3.mlp.gate_up_proj", "visual.blocks.3.mlp.gate_proj", "visual.blocks.3.mlp.up_proj", "visual.blocks.4.mlp.down_proj", "visual.blocks.4.mlp.gate_up_proj", "visual.blocks.4.mlp.gate_proj", "visual.blocks.4.mlp.up_proj", "visual.merger.post_projection_norm", "visual.blocks.12.attn.proj", "visual.blocks.13.attn.proj", "visual.blocks.14.attn.proj", "visual.blocks.15.attn.proj", "visual.blocks.16.attn.proj", "visual.blocks.17.attn.proj", "visual.blocks.18.attn.proj", "visual.blocks.19.attn.proj", "visual.blocks.20.attn.proj", "visual.blocks.21.attn.proj", "visual.blocks.5.mlp.down_proj", "visual.blocks.6.mlp.down_proj", "visual.blocks.7.mlp.down_proj", "visual.blocks.8.mlp.down_proj", "visual.blocks.9.mlp.down_proj", "visual.blocks.0.attn.proj", "visual.blocks.1.attn.proj", "visual.blocks.2.attn.proj", "visual.blocks.3.attn.proj", "visual.blocks.4.attn.proj", "visual.blocks.5.attn.proj", "visual.blocks.6.attn.proj", "visual.blocks.7.attn.proj", "visual.blocks.8.attn.proj", "visual.blocks.9.attn.proj", "visual.blocks.12.attn.qkv_proj", "visual.blocks.13.attn.qkv_proj", "visual.blocks.14.attn.qkv_proj", "visual.blocks.15.attn.qkv_proj", "visual.blocks.16.attn.qkv_proj", "visual.blocks.17.attn.qkv_proj", "visual.blocks.18.attn.qkv_proj", "model.layers.34.self_attn.v_proj.bias", "model.layers.35.self_attn.v_proj.bias", "model.layers.36.self_attn.v_proj.bias", "model.layers.37.self_attn.v_proj.bias", "model.layers.38.self_attn.v_proj.bias", "model.layers.39.self_attn.v_proj.bias", "model.layers.40.self_attn.v_proj.bias", "model.layers.41.self_attn.v_proj.bias", "model.layers.42.self_attn.v_proj.bias", "model.layers.30.self_attn.v_proj.bias", "model.layers.2.self_attn.q_proj.bias", "model.layers.4.self_attn.q_proj.bias", "model.layers.3.self_attn.q_proj.bias", "model.layers.0.self_attn.q_proj.bias", "model.layers.1.self_attn.q_proj.bias", "model.layers.8.self_attn.q_proj.bias", "model.layers.6.self_attn.q_proj.bias", "model.layers.7.self_attn.q_proj.bias", "model.layers.5.self_attn.q_proj.bias", "model.layers.9.self_attn.q_proj.bias", "model.layers.2.self_attn.v_proj.bias", "model.layers.4.self_attn.v_proj.bias", "model.layers.3.self_attn.v_proj.bias", "model.layers.0.self_attn.v_proj.bias", "model.layers.1.self_attn.v_proj.bias", "model.layers.8.self_attn.v_proj.bias", "model.layers.6.self_attn.v_proj.bias", "model.layers.7.self_attn.v_proj.bias", "model.layers.18.mlp.gate", "model.layers.19.mlp.gate", "model.layers.20.mlp.gate", "model.layers.22.mlp.gate", "model.layers.21.mlp.gate", "model.layers.23.mlp.gate", "model.layers.24.mlp.gate", "model.layers.25.mlp.gate", "model.layers.26.mlp.gate", "model.layers.27.mlp.gate", "model.layers.43.mlp.gate.e_score_correction_bias", "model.layers.44.mlp.gate.e_score_correction_bias", "model.layers.19.input_layernorm", "model.layers.20.input_layernorm", "model.layers.22.input_layernorm", "model.layers.43.input_layernorm", "model.layers.44.input_layernorm", "model.layers.45.input_layernorm", "model.layers.2.post_attention_layernorm", "model.layers.4.post_attention_layernorm", "model.layers.3.post_attention_layernorm", "model.layers.0.post_attention_layernorm", "model.layers.1.post_attention_layernorm", "model.layers.8.post_attention_layernorm", "model.layers.6.post_attention_layernorm", "model.layers.7.post_attention_layernorm", "model.layers.5.post_attention_layernorm", "model.layers.9.post_attention_layernorm", "visual.downsample" ], "quant_method": "compressed-tensors", "quantization_status": "compressed" } }