| { | |
| "_name_or_path": "/network/shubhra/Pixtral-Large-Instruct-2411-pr23/", | |
| "architectures": [ | |
| "LlavaForConditionalGeneration" | |
| ], | |
| "ignore_index": -100, | |
| "image_seq_length": 1, | |
| "image_token_index": 10, | |
| "model_type": "llava", | |
| "multimodal_projector_bias": false, | |
| "projector_hidden_act": "gelu", | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": null, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": "weight", | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": 128, | |
| "num_bits": 4, | |
| "observer": "minmax", | |
| "observer_kwargs": {}, | |
| "strategy": "group", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "pack-quantized", | |
| "global_compression_ratio": 1.5568737751955632, | |
| "ignore": [ | |
| "vision_tower.transformer.layers.0.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.0.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.0.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.0.attention.k_proj", | |
| "vision_tower.transformer.layers.0.attention.v_proj", | |
| "vision_tower.transformer.layers.0.attention.q_proj", | |
| "vision_tower.transformer.layers.0.attention.o_proj", | |
| "vision_tower.transformer.layers.1.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.1.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.1.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.1.attention.k_proj", | |
| "vision_tower.transformer.layers.1.attention.v_proj", | |
| "vision_tower.transformer.layers.1.attention.q_proj", | |
| "vision_tower.transformer.layers.1.attention.o_proj", | |
| "vision_tower.transformer.layers.2.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.2.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.2.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.2.attention.k_proj", | |
| "vision_tower.transformer.layers.2.attention.v_proj", | |
| "vision_tower.transformer.layers.2.attention.q_proj", | |
| "vision_tower.transformer.layers.2.attention.o_proj", | |
| "vision_tower.transformer.layers.3.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.3.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.3.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.3.attention.k_proj", | |
| "vision_tower.transformer.layers.3.attention.v_proj", | |
| "vision_tower.transformer.layers.3.attention.q_proj", | |
| "vision_tower.transformer.layers.3.attention.o_proj", | |
| "vision_tower.transformer.layers.4.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.4.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.4.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.4.attention.k_proj", | |
| "vision_tower.transformer.layers.4.attention.v_proj", | |
| "vision_tower.transformer.layers.4.attention.q_proj", | |
| "vision_tower.transformer.layers.4.attention.o_proj", | |
| "vision_tower.transformer.layers.5.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.5.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.5.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.5.attention.k_proj", | |
| "vision_tower.transformer.layers.5.attention.v_proj", | |
| "vision_tower.transformer.layers.5.attention.q_proj", | |
| "vision_tower.transformer.layers.5.attention.o_proj", | |
| "vision_tower.transformer.layers.6.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.6.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.6.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.6.attention.k_proj", | |
| "vision_tower.transformer.layers.6.attention.v_proj", | |
| "vision_tower.transformer.layers.6.attention.q_proj", | |
| "vision_tower.transformer.layers.6.attention.o_proj", | |
| "vision_tower.transformer.layers.7.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.7.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.7.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.7.attention.k_proj", | |
| "vision_tower.transformer.layers.7.attention.v_proj", | |
| "vision_tower.transformer.layers.7.attention.q_proj", | |
| "vision_tower.transformer.layers.7.attention.o_proj", | |
| "vision_tower.transformer.layers.8.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.8.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.8.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.8.attention.k_proj", | |
| "vision_tower.transformer.layers.8.attention.v_proj", | |
| "vision_tower.transformer.layers.8.attention.q_proj", | |
| "vision_tower.transformer.layers.8.attention.o_proj", | |
| "vision_tower.transformer.layers.9.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.9.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.9.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.9.attention.k_proj", | |
| "vision_tower.transformer.layers.9.attention.v_proj", | |
| "vision_tower.transformer.layers.9.attention.q_proj", | |
| "vision_tower.transformer.layers.9.attention.o_proj", | |
| "vision_tower.transformer.layers.10.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.10.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.10.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.10.attention.k_proj", | |
| "vision_tower.transformer.layers.10.attention.v_proj", | |
| "vision_tower.transformer.layers.10.attention.q_proj", | |
| "vision_tower.transformer.layers.10.attention.o_proj", | |
| "vision_tower.transformer.layers.11.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.11.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.11.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.11.attention.k_proj", | |
| "vision_tower.transformer.layers.11.attention.v_proj", | |
| "vision_tower.transformer.layers.11.attention.q_proj", | |
| "vision_tower.transformer.layers.11.attention.o_proj", | |
| "vision_tower.transformer.layers.12.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.12.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.12.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.12.attention.k_proj", | |
| "vision_tower.transformer.layers.12.attention.v_proj", | |
| "vision_tower.transformer.layers.12.attention.q_proj", | |
| "vision_tower.transformer.layers.12.attention.o_proj", | |
| "vision_tower.transformer.layers.13.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.13.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.13.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.13.attention.k_proj", | |
| "vision_tower.transformer.layers.13.attention.v_proj", | |
| "vision_tower.transformer.layers.13.attention.q_proj", | |
| "vision_tower.transformer.layers.13.attention.o_proj", | |
| "vision_tower.transformer.layers.14.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.14.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.14.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.14.attention.k_proj", | |
| "vision_tower.transformer.layers.14.attention.v_proj", | |
| "vision_tower.transformer.layers.14.attention.q_proj", | |
| "vision_tower.transformer.layers.14.attention.o_proj", | |
| "vision_tower.transformer.layers.15.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.15.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.15.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.15.attention.k_proj", | |
| "vision_tower.transformer.layers.15.attention.v_proj", | |
| "vision_tower.transformer.layers.15.attention.q_proj", | |
| "vision_tower.transformer.layers.15.attention.o_proj", | |
| "vision_tower.transformer.layers.16.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.16.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.16.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.16.attention.k_proj", | |
| "vision_tower.transformer.layers.16.attention.v_proj", | |
| "vision_tower.transformer.layers.16.attention.q_proj", | |
| "vision_tower.transformer.layers.16.attention.o_proj", | |
| "vision_tower.transformer.layers.17.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.17.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.17.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.17.attention.k_proj", | |
| "vision_tower.transformer.layers.17.attention.v_proj", | |
| "vision_tower.transformer.layers.17.attention.q_proj", | |
| "vision_tower.transformer.layers.17.attention.o_proj", | |
| "vision_tower.transformer.layers.18.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.18.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.18.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.18.attention.k_proj", | |
| "vision_tower.transformer.layers.18.attention.v_proj", | |
| "vision_tower.transformer.layers.18.attention.q_proj", | |
| "vision_tower.transformer.layers.18.attention.o_proj", | |
| "vision_tower.transformer.layers.19.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.19.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.19.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.19.attention.k_proj", | |
| "vision_tower.transformer.layers.19.attention.v_proj", | |
| "vision_tower.transformer.layers.19.attention.q_proj", | |
| "vision_tower.transformer.layers.19.attention.o_proj", | |
| "vision_tower.transformer.layers.20.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.20.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.20.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.20.attention.k_proj", | |
| "vision_tower.transformer.layers.20.attention.v_proj", | |
| "vision_tower.transformer.layers.20.attention.q_proj", | |
| "vision_tower.transformer.layers.20.attention.o_proj", | |
| "vision_tower.transformer.layers.21.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.21.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.21.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.21.attention.k_proj", | |
| "vision_tower.transformer.layers.21.attention.v_proj", | |
| "vision_tower.transformer.layers.21.attention.q_proj", | |
| "vision_tower.transformer.layers.21.attention.o_proj", | |
| "vision_tower.transformer.layers.22.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.22.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.22.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.22.attention.k_proj", | |
| "vision_tower.transformer.layers.22.attention.v_proj", | |
| "vision_tower.transformer.layers.22.attention.q_proj", | |
| "vision_tower.transformer.layers.22.attention.o_proj", | |
| "vision_tower.transformer.layers.23.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.23.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.23.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.23.attention.k_proj", | |
| "vision_tower.transformer.layers.23.attention.v_proj", | |
| "vision_tower.transformer.layers.23.attention.q_proj", | |
| "vision_tower.transformer.layers.23.attention.o_proj", | |
| "vision_tower.transformer.layers.24.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.24.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.24.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.24.attention.k_proj", | |
| "vision_tower.transformer.layers.24.attention.v_proj", | |
| "vision_tower.transformer.layers.24.attention.q_proj", | |
| "vision_tower.transformer.layers.24.attention.o_proj", | |
| "vision_tower.transformer.layers.25.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.25.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.25.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.25.attention.k_proj", | |
| "vision_tower.transformer.layers.25.attention.v_proj", | |
| "vision_tower.transformer.layers.25.attention.q_proj", | |
| "vision_tower.transformer.layers.25.attention.o_proj", | |
| "vision_tower.transformer.layers.26.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.26.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.26.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.26.attention.k_proj", | |
| "vision_tower.transformer.layers.26.attention.v_proj", | |
| "vision_tower.transformer.layers.26.attention.q_proj", | |
| "vision_tower.transformer.layers.26.attention.o_proj", | |
| "vision_tower.transformer.layers.27.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.27.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.27.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.27.attention.k_proj", | |
| "vision_tower.transformer.layers.27.attention.v_proj", | |
| "vision_tower.transformer.layers.27.attention.q_proj", | |
| "vision_tower.transformer.layers.27.attention.o_proj", | |
| "vision_tower.transformer.layers.28.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.28.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.28.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.28.attention.k_proj", | |
| "vision_tower.transformer.layers.28.attention.v_proj", | |
| "vision_tower.transformer.layers.28.attention.q_proj", | |
| "vision_tower.transformer.layers.28.attention.o_proj", | |
| "vision_tower.transformer.layers.29.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.29.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.29.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.29.attention.k_proj", | |
| "vision_tower.transformer.layers.29.attention.v_proj", | |
| "vision_tower.transformer.layers.29.attention.q_proj", | |
| "vision_tower.transformer.layers.29.attention.o_proj", | |
| "vision_tower.transformer.layers.30.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.30.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.30.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.30.attention.k_proj", | |
| "vision_tower.transformer.layers.30.attention.v_proj", | |
| "vision_tower.transformer.layers.30.attention.q_proj", | |
| "vision_tower.transformer.layers.30.attention.o_proj", | |
| "vision_tower.transformer.layers.31.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.31.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.31.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.31.attention.k_proj", | |
| "vision_tower.transformer.layers.31.attention.v_proj", | |
| "vision_tower.transformer.layers.31.attention.q_proj", | |
| "vision_tower.transformer.layers.31.attention.o_proj", | |
| "vision_tower.transformer.layers.32.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.32.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.32.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.32.attention.k_proj", | |
| "vision_tower.transformer.layers.32.attention.v_proj", | |
| "vision_tower.transformer.layers.32.attention.q_proj", | |
| "vision_tower.transformer.layers.32.attention.o_proj", | |
| "vision_tower.transformer.layers.33.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.33.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.33.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.33.attention.k_proj", | |
| "vision_tower.transformer.layers.33.attention.v_proj", | |
| "vision_tower.transformer.layers.33.attention.q_proj", | |
| "vision_tower.transformer.layers.33.attention.o_proj", | |
| "vision_tower.transformer.layers.34.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.34.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.34.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.34.attention.k_proj", | |
| "vision_tower.transformer.layers.34.attention.v_proj", | |
| "vision_tower.transformer.layers.34.attention.q_proj", | |
| "vision_tower.transformer.layers.34.attention.o_proj", | |
| "vision_tower.transformer.layers.35.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.35.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.35.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.35.attention.k_proj", | |
| "vision_tower.transformer.layers.35.attention.v_proj", | |
| "vision_tower.transformer.layers.35.attention.q_proj", | |
| "vision_tower.transformer.layers.35.attention.o_proj", | |
| "vision_tower.transformer.layers.36.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.36.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.36.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.36.attention.k_proj", | |
| "vision_tower.transformer.layers.36.attention.v_proj", | |
| "vision_tower.transformer.layers.36.attention.q_proj", | |
| "vision_tower.transformer.layers.36.attention.o_proj", | |
| "vision_tower.transformer.layers.37.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.37.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.37.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.37.attention.k_proj", | |
| "vision_tower.transformer.layers.37.attention.v_proj", | |
| "vision_tower.transformer.layers.37.attention.q_proj", | |
| "vision_tower.transformer.layers.37.attention.o_proj", | |
| "vision_tower.transformer.layers.38.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.38.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.38.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.38.attention.k_proj", | |
| "vision_tower.transformer.layers.38.attention.v_proj", | |
| "vision_tower.transformer.layers.38.attention.q_proj", | |
| "vision_tower.transformer.layers.38.attention.o_proj", | |
| "vision_tower.transformer.layers.39.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.39.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.39.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.39.attention.k_proj", | |
| "vision_tower.transformer.layers.39.attention.v_proj", | |
| "vision_tower.transformer.layers.39.attention.q_proj", | |
| "vision_tower.transformer.layers.39.attention.o_proj", | |
| "multi_modal_projector.linear_1", | |
| "multi_modal_projector.linear_2", | |
| "language_model.lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed", | |
| "sparsity_config": { | |
| "format": "dense", | |
| "global_sparsity": 0.15425385709456318, | |
| "ignore": [ | |
| "vision_tower.transformer.layers.0.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.0.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.0.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.0.attention.k_proj", | |
| "vision_tower.transformer.layers.0.attention.v_proj", | |
| "vision_tower.transformer.layers.0.attention.q_proj", | |
| "vision_tower.transformer.layers.0.attention.o_proj", | |
| "vision_tower.transformer.layers.1.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.1.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.1.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.1.attention.k_proj", | |
| "vision_tower.transformer.layers.1.attention.v_proj", | |
| "vision_tower.transformer.layers.1.attention.q_proj", | |
| "vision_tower.transformer.layers.1.attention.o_proj", | |
| "vision_tower.transformer.layers.2.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.2.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.2.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.2.attention.k_proj", | |
| "vision_tower.transformer.layers.2.attention.v_proj", | |
| "vision_tower.transformer.layers.2.attention.q_proj", | |
| "vision_tower.transformer.layers.2.attention.o_proj", | |
| "vision_tower.transformer.layers.3.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.3.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.3.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.3.attention.k_proj", | |
| "vision_tower.transformer.layers.3.attention.v_proj", | |
| "vision_tower.transformer.layers.3.attention.q_proj", | |
| "vision_tower.transformer.layers.3.attention.o_proj", | |
| "vision_tower.transformer.layers.4.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.4.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.4.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.4.attention.k_proj", | |
| "vision_tower.transformer.layers.4.attention.v_proj", | |
| "vision_tower.transformer.layers.4.attention.q_proj", | |
| "vision_tower.transformer.layers.4.attention.o_proj", | |
| "vision_tower.transformer.layers.5.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.5.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.5.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.5.attention.k_proj", | |
| "vision_tower.transformer.layers.5.attention.v_proj", | |
| "vision_tower.transformer.layers.5.attention.q_proj", | |
| "vision_tower.transformer.layers.5.attention.o_proj", | |
| "vision_tower.transformer.layers.6.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.6.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.6.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.6.attention.k_proj", | |
| "vision_tower.transformer.layers.6.attention.v_proj", | |
| "vision_tower.transformer.layers.6.attention.q_proj", | |
| "vision_tower.transformer.layers.6.attention.o_proj", | |
| "vision_tower.transformer.layers.7.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.7.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.7.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.7.attention.k_proj", | |
| "vision_tower.transformer.layers.7.attention.v_proj", | |
| "vision_tower.transformer.layers.7.attention.q_proj", | |
| "vision_tower.transformer.layers.7.attention.o_proj", | |
| "vision_tower.transformer.layers.8.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.8.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.8.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.8.attention.k_proj", | |
| "vision_tower.transformer.layers.8.attention.v_proj", | |
| "vision_tower.transformer.layers.8.attention.q_proj", | |
| "vision_tower.transformer.layers.8.attention.o_proj", | |
| "vision_tower.transformer.layers.9.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.9.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.9.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.9.attention.k_proj", | |
| "vision_tower.transformer.layers.9.attention.v_proj", | |
| "vision_tower.transformer.layers.9.attention.q_proj", | |
| "vision_tower.transformer.layers.9.attention.o_proj", | |
| "vision_tower.transformer.layers.10.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.10.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.10.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.10.attention.k_proj", | |
| "vision_tower.transformer.layers.10.attention.v_proj", | |
| "vision_tower.transformer.layers.10.attention.q_proj", | |
| "vision_tower.transformer.layers.10.attention.o_proj", | |
| "vision_tower.transformer.layers.11.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.11.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.11.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.11.attention.k_proj", | |
| "vision_tower.transformer.layers.11.attention.v_proj", | |
| "vision_tower.transformer.layers.11.attention.q_proj", | |
| "vision_tower.transformer.layers.11.attention.o_proj", | |
| "vision_tower.transformer.layers.12.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.12.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.12.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.12.attention.k_proj", | |
| "vision_tower.transformer.layers.12.attention.v_proj", | |
| "vision_tower.transformer.layers.12.attention.q_proj", | |
| "vision_tower.transformer.layers.12.attention.o_proj", | |
| "vision_tower.transformer.layers.13.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.13.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.13.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.13.attention.k_proj", | |
| "vision_tower.transformer.layers.13.attention.v_proj", | |
| "vision_tower.transformer.layers.13.attention.q_proj", | |
| "vision_tower.transformer.layers.13.attention.o_proj", | |
| "vision_tower.transformer.layers.14.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.14.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.14.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.14.attention.k_proj", | |
| "vision_tower.transformer.layers.14.attention.v_proj", | |
| "vision_tower.transformer.layers.14.attention.q_proj", | |
| "vision_tower.transformer.layers.14.attention.o_proj", | |
| "vision_tower.transformer.layers.15.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.15.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.15.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.15.attention.k_proj", | |
| "vision_tower.transformer.layers.15.attention.v_proj", | |
| "vision_tower.transformer.layers.15.attention.q_proj", | |
| "vision_tower.transformer.layers.15.attention.o_proj", | |
| "vision_tower.transformer.layers.16.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.16.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.16.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.16.attention.k_proj", | |
| "vision_tower.transformer.layers.16.attention.v_proj", | |
| "vision_tower.transformer.layers.16.attention.q_proj", | |
| "vision_tower.transformer.layers.16.attention.o_proj", | |
| "vision_tower.transformer.layers.17.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.17.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.17.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.17.attention.k_proj", | |
| "vision_tower.transformer.layers.17.attention.v_proj", | |
| "vision_tower.transformer.layers.17.attention.q_proj", | |
| "vision_tower.transformer.layers.17.attention.o_proj", | |
| "vision_tower.transformer.layers.18.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.18.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.18.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.18.attention.k_proj", | |
| "vision_tower.transformer.layers.18.attention.v_proj", | |
| "vision_tower.transformer.layers.18.attention.q_proj", | |
| "vision_tower.transformer.layers.18.attention.o_proj", | |
| "vision_tower.transformer.layers.19.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.19.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.19.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.19.attention.k_proj", | |
| "vision_tower.transformer.layers.19.attention.v_proj", | |
| "vision_tower.transformer.layers.19.attention.q_proj", | |
| "vision_tower.transformer.layers.19.attention.o_proj", | |
| "vision_tower.transformer.layers.20.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.20.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.20.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.20.attention.k_proj", | |
| "vision_tower.transformer.layers.20.attention.v_proj", | |
| "vision_tower.transformer.layers.20.attention.q_proj", | |
| "vision_tower.transformer.layers.20.attention.o_proj", | |
| "vision_tower.transformer.layers.21.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.21.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.21.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.21.attention.k_proj", | |
| "vision_tower.transformer.layers.21.attention.v_proj", | |
| "vision_tower.transformer.layers.21.attention.q_proj", | |
| "vision_tower.transformer.layers.21.attention.o_proj", | |
| "vision_tower.transformer.layers.22.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.22.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.22.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.22.attention.k_proj", | |
| "vision_tower.transformer.layers.22.attention.v_proj", | |
| "vision_tower.transformer.layers.22.attention.q_proj", | |
| "vision_tower.transformer.layers.22.attention.o_proj", | |
| "vision_tower.transformer.layers.23.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.23.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.23.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.23.attention.k_proj", | |
| "vision_tower.transformer.layers.23.attention.v_proj", | |
| "vision_tower.transformer.layers.23.attention.q_proj", | |
| "vision_tower.transformer.layers.23.attention.o_proj", | |
| "vision_tower.transformer.layers.24.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.24.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.24.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.24.attention.k_proj", | |
| "vision_tower.transformer.layers.24.attention.v_proj", | |
| "vision_tower.transformer.layers.24.attention.q_proj", | |
| "vision_tower.transformer.layers.24.attention.o_proj", | |
| "vision_tower.transformer.layers.25.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.25.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.25.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.25.attention.k_proj", | |
| "vision_tower.transformer.layers.25.attention.v_proj", | |
| "vision_tower.transformer.layers.25.attention.q_proj", | |
| "vision_tower.transformer.layers.25.attention.o_proj", | |
| "vision_tower.transformer.layers.26.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.26.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.26.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.26.attention.k_proj", | |
| "vision_tower.transformer.layers.26.attention.v_proj", | |
| "vision_tower.transformer.layers.26.attention.q_proj", | |
| "vision_tower.transformer.layers.26.attention.o_proj", | |
| "vision_tower.transformer.layers.27.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.27.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.27.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.27.attention.k_proj", | |
| "vision_tower.transformer.layers.27.attention.v_proj", | |
| "vision_tower.transformer.layers.27.attention.q_proj", | |
| "vision_tower.transformer.layers.27.attention.o_proj", | |
| "vision_tower.transformer.layers.28.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.28.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.28.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.28.attention.k_proj", | |
| "vision_tower.transformer.layers.28.attention.v_proj", | |
| "vision_tower.transformer.layers.28.attention.q_proj", | |
| "vision_tower.transformer.layers.28.attention.o_proj", | |
| "vision_tower.transformer.layers.29.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.29.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.29.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.29.attention.k_proj", | |
| "vision_tower.transformer.layers.29.attention.v_proj", | |
| "vision_tower.transformer.layers.29.attention.q_proj", | |
| "vision_tower.transformer.layers.29.attention.o_proj", | |
| "vision_tower.transformer.layers.30.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.30.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.30.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.30.attention.k_proj", | |
| "vision_tower.transformer.layers.30.attention.v_proj", | |
| "vision_tower.transformer.layers.30.attention.q_proj", | |
| "vision_tower.transformer.layers.30.attention.o_proj", | |
| "vision_tower.transformer.layers.31.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.31.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.31.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.31.attention.k_proj", | |
| "vision_tower.transformer.layers.31.attention.v_proj", | |
| "vision_tower.transformer.layers.31.attention.q_proj", | |
| "vision_tower.transformer.layers.31.attention.o_proj", | |
| "vision_tower.transformer.layers.32.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.32.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.32.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.32.attention.k_proj", | |
| "vision_tower.transformer.layers.32.attention.v_proj", | |
| "vision_tower.transformer.layers.32.attention.q_proj", | |
| "vision_tower.transformer.layers.32.attention.o_proj", | |
| "vision_tower.transformer.layers.33.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.33.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.33.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.33.attention.k_proj", | |
| "vision_tower.transformer.layers.33.attention.v_proj", | |
| "vision_tower.transformer.layers.33.attention.q_proj", | |
| "vision_tower.transformer.layers.33.attention.o_proj", | |
| "vision_tower.transformer.layers.34.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.34.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.34.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.34.attention.k_proj", | |
| "vision_tower.transformer.layers.34.attention.v_proj", | |
| "vision_tower.transformer.layers.34.attention.q_proj", | |
| "vision_tower.transformer.layers.34.attention.o_proj", | |
| "vision_tower.transformer.layers.35.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.35.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.35.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.35.attention.k_proj", | |
| "vision_tower.transformer.layers.35.attention.v_proj", | |
| "vision_tower.transformer.layers.35.attention.q_proj", | |
| "vision_tower.transformer.layers.35.attention.o_proj", | |
| "vision_tower.transformer.layers.36.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.36.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.36.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.36.attention.k_proj", | |
| "vision_tower.transformer.layers.36.attention.v_proj", | |
| "vision_tower.transformer.layers.36.attention.q_proj", | |
| "vision_tower.transformer.layers.36.attention.o_proj", | |
| "vision_tower.transformer.layers.37.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.37.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.37.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.37.attention.k_proj", | |
| "vision_tower.transformer.layers.37.attention.v_proj", | |
| "vision_tower.transformer.layers.37.attention.q_proj", | |
| "vision_tower.transformer.layers.37.attention.o_proj", | |
| "vision_tower.transformer.layers.38.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.38.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.38.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.38.attention.k_proj", | |
| "vision_tower.transformer.layers.38.attention.v_proj", | |
| "vision_tower.transformer.layers.38.attention.q_proj", | |
| "vision_tower.transformer.layers.38.attention.o_proj", | |
| "vision_tower.transformer.layers.39.feed_forward.gate_proj", | |
| "vision_tower.transformer.layers.39.feed_forward.up_proj", | |
| "vision_tower.transformer.layers.39.feed_forward.down_proj", | |
| "vision_tower.transformer.layers.39.attention.k_proj", | |
| "vision_tower.transformer.layers.39.attention.v_proj", | |
| "vision_tower.transformer.layers.39.attention.q_proj", | |
| "vision_tower.transformer.layers.39.attention.o_proj", | |
| "multi_modal_projector.linear_1", | |
| "multi_modal_projector.linear_2", | |
| "language_model.model.layers.0.self_attn.v_proj", | |
| "language_model.model.layers.0.self_attn.o_proj", | |
| "language_model.model.layers.0.mlp.gate_proj", | |
| "language_model.model.layers.0.mlp.up_proj", | |
| "language_model.model.layers.0.mlp.down_proj", | |
| "language_model.model.layers.1.self_attn.q_proj", | |
| "language_model.model.layers.1.self_attn.k_proj", | |
| "language_model.model.layers.1.self_attn.v_proj", | |
| "language_model.model.layers.1.self_attn.o_proj", | |
| "language_model.model.layers.1.mlp.gate_proj", | |
| "language_model.model.layers.1.mlp.up_proj", | |
| "language_model.model.layers.1.mlp.down_proj", | |
| "language_model.model.layers.2.self_attn.q_proj", | |
| "language_model.model.layers.2.self_attn.k_proj", | |
| "language_model.model.layers.2.self_attn.v_proj", | |
| "language_model.model.layers.2.self_attn.o_proj", | |
| "language_model.model.layers.2.mlp.gate_proj", | |
| "language_model.model.layers.2.mlp.up_proj", | |
| "language_model.model.layers.2.mlp.down_proj", | |
| "language_model.model.layers.3.self_attn.q_proj", | |
| "language_model.model.layers.3.self_attn.k_proj", | |
| "language_model.model.layers.3.self_attn.v_proj", | |
| "language_model.model.layers.3.self_attn.o_proj", | |
| "language_model.model.layers.3.mlp.gate_proj", | |
| "language_model.model.layers.3.mlp.up_proj", | |
| "language_model.model.layers.3.mlp.down_proj", | |
| "language_model.model.layers.4.self_attn.q_proj", | |
| "language_model.model.layers.4.self_attn.k_proj", | |
| "language_model.model.layers.4.self_attn.v_proj", | |
| "language_model.model.layers.4.self_attn.o_proj", | |
| "language_model.model.layers.4.mlp.gate_proj", | |
| "language_model.model.layers.4.mlp.up_proj", | |
| "language_model.model.layers.4.mlp.down_proj", | |
| "language_model.model.layers.5.self_attn.q_proj", | |
| "language_model.model.layers.5.self_attn.k_proj", | |
| "language_model.model.layers.5.self_attn.v_proj", | |
| "language_model.model.layers.5.self_attn.o_proj", | |
| "language_model.model.layers.5.mlp.gate_proj", | |
| "language_model.model.layers.5.mlp.up_proj", | |
| "language_model.model.layers.5.mlp.down_proj", | |
| "language_model.model.layers.6.self_attn.q_proj", | |
| "language_model.model.layers.6.self_attn.k_proj", | |
| "language_model.model.layers.6.self_attn.v_proj", | |
| "language_model.model.layers.6.self_attn.o_proj", | |
| "language_model.model.layers.6.mlp.gate_proj", | |
| "language_model.model.layers.6.mlp.up_proj", | |
| "language_model.model.layers.6.mlp.down_proj", | |
| "language_model.model.layers.7.self_attn.q_proj", | |
| "language_model.model.layers.7.self_attn.k_proj", | |
| "language_model.model.layers.7.self_attn.v_proj", | |
| "language_model.model.layers.7.self_attn.o_proj", | |
| "language_model.model.layers.7.mlp.gate_proj", | |
| "language_model.model.layers.7.mlp.up_proj", | |
| "language_model.model.layers.7.mlp.down_proj", | |
| "language_model.model.layers.8.self_attn.q_proj", | |
| "language_model.model.layers.8.self_attn.k_proj", | |
| "language_model.model.layers.8.self_attn.v_proj", | |
| "language_model.model.layers.8.self_attn.o_proj", | |
| "language_model.model.layers.8.mlp.gate_proj", | |
| "language_model.model.layers.8.mlp.up_proj", | |
| "language_model.model.layers.8.mlp.down_proj", | |
| "language_model.model.layers.9.self_attn.q_proj", | |
| "language_model.model.layers.9.self_attn.k_proj", | |
| "language_model.model.layers.9.self_attn.v_proj", | |
| "language_model.model.layers.9.self_attn.o_proj", | |
| "language_model.model.layers.9.mlp.gate_proj", | |
| "language_model.model.layers.9.mlp.up_proj", | |
| "language_model.model.layers.9.mlp.down_proj", | |
| "language_model.model.layers.10.self_attn.q_proj", | |
| "language_model.model.layers.10.self_attn.k_proj", | |
| "language_model.model.layers.10.self_attn.v_proj", | |
| "language_model.model.layers.10.self_attn.o_proj", | |
| "language_model.model.layers.10.mlp.gate_proj", | |
| "language_model.model.layers.10.mlp.up_proj", | |
| "language_model.model.layers.10.mlp.down_proj", | |
| "language_model.model.layers.11.self_attn.q_proj", | |
| "language_model.model.layers.11.self_attn.k_proj", | |
| "language_model.model.layers.11.self_attn.v_proj", | |
| "language_model.model.layers.11.self_attn.o_proj", | |
| "language_model.model.layers.11.mlp.gate_proj", | |
| "language_model.model.layers.11.mlp.up_proj", | |
| "language_model.model.layers.11.mlp.down_proj", | |
| "language_model.model.layers.12.self_attn.q_proj", | |
| "language_model.model.layers.12.self_attn.k_proj", | |
| "language_model.model.layers.12.self_attn.v_proj", | |
| "language_model.model.layers.12.self_attn.o_proj", | |
| "language_model.model.layers.12.mlp.gate_proj", | |
| "language_model.model.layers.12.mlp.up_proj", | |
| "language_model.model.layers.12.mlp.down_proj", | |
| "language_model.model.layers.13.self_attn.q_proj", | |
| "language_model.model.layers.13.self_attn.k_proj", | |
| "language_model.model.layers.13.self_attn.v_proj", | |
| "language_model.model.layers.13.self_attn.o_proj", | |
| "language_model.model.layers.13.mlp.gate_proj", | |
| "language_model.model.layers.13.mlp.up_proj", | |
| "language_model.model.layers.13.mlp.down_proj", | |
| "language_model.model.layers.14.self_attn.q_proj", | |
| "language_model.model.layers.14.self_attn.k_proj", | |
| "language_model.model.layers.14.self_attn.v_proj", | |
| "language_model.model.layers.14.self_attn.o_proj", | |
| "language_model.model.layers.14.mlp.gate_proj", | |
| "language_model.model.layers.14.mlp.up_proj", | |
| "language_model.model.layers.14.mlp.down_proj", | |
| "language_model.model.layers.15.self_attn.q_proj", | |
| "language_model.model.layers.15.self_attn.k_proj", | |
| "language_model.model.layers.15.self_attn.v_proj", | |
| "language_model.model.layers.15.self_attn.o_proj", | |
| "language_model.model.layers.15.mlp.gate_proj", | |
| "language_model.model.layers.15.mlp.up_proj", | |
| "language_model.model.layers.15.mlp.down_proj", | |
| "language_model.model.layers.16.self_attn.q_proj", | |
| "language_model.model.layers.16.self_attn.k_proj", | |
| "language_model.model.layers.16.self_attn.v_proj", | |
| "language_model.model.layers.16.self_attn.o_proj", | |
| "language_model.model.layers.16.mlp.gate_proj", | |
| "language_model.model.layers.16.mlp.up_proj", | |
| "language_model.model.layers.16.mlp.down_proj", | |
| "language_model.model.layers.17.self_attn.q_proj", | |
| "language_model.model.layers.17.self_attn.k_proj", | |
| "language_model.model.layers.17.self_attn.v_proj", | |
| "language_model.model.layers.17.self_attn.o_proj", | |
| "language_model.model.layers.17.mlp.gate_proj", | |
| "language_model.model.layers.17.mlp.up_proj", | |
| "language_model.model.layers.17.mlp.down_proj", | |
| "language_model.model.layers.18.self_attn.q_proj", | |
| "language_model.model.layers.18.self_attn.k_proj", | |
| "language_model.model.layers.18.self_attn.v_proj", | |
| "language_model.model.layers.18.self_attn.o_proj", | |
| "language_model.model.layers.18.mlp.gate_proj", | |
| "language_model.model.layers.18.mlp.up_proj", | |
| "language_model.model.layers.18.mlp.down_proj", | |
| "language_model.model.layers.19.self_attn.q_proj", | |
| "language_model.model.layers.19.self_attn.k_proj", | |
| "language_model.model.layers.19.self_attn.v_proj", | |
| "language_model.model.layers.19.self_attn.o_proj", | |
| "language_model.model.layers.19.mlp.gate_proj", | |
| "language_model.model.layers.19.mlp.up_proj", | |
| "language_model.model.layers.19.mlp.down_proj", | |
| "language_model.model.layers.20.self_attn.q_proj", | |
| "language_model.model.layers.20.self_attn.k_proj", | |
| "language_model.model.layers.20.self_attn.v_proj", | |
| "language_model.model.layers.20.self_attn.o_proj", | |
| "language_model.model.layers.20.mlp.gate_proj", | |
| "language_model.model.layers.20.mlp.up_proj", | |
| "language_model.model.layers.20.mlp.down_proj", | |
| "language_model.model.layers.21.self_attn.q_proj", | |
| "language_model.model.layers.21.self_attn.k_proj", | |
| "language_model.model.layers.21.self_attn.v_proj", | |
| "language_model.model.layers.21.self_attn.o_proj", | |
| "language_model.model.layers.21.mlp.gate_proj", | |
| "language_model.model.layers.21.mlp.up_proj", | |
| "language_model.model.layers.21.mlp.down_proj", | |
| "language_model.model.layers.22.self_attn.q_proj", | |
| "language_model.model.layers.22.self_attn.k_proj", | |
| "language_model.model.layers.22.self_attn.v_proj", | |
| "language_model.model.layers.22.self_attn.o_proj", | |
| "language_model.model.layers.22.mlp.gate_proj", | |
| "language_model.model.layers.22.mlp.up_proj", | |
| "language_model.model.layers.22.mlp.down_proj", | |
| "language_model.model.layers.23.self_attn.q_proj", | |
| "language_model.model.layers.23.self_attn.k_proj", | |
| "language_model.model.layers.23.self_attn.v_proj", | |
| "language_model.model.layers.23.self_attn.o_proj", | |
| "language_model.model.layers.23.mlp.gate_proj", | |
| "language_model.model.layers.23.mlp.up_proj", | |
| "language_model.model.layers.23.mlp.down_proj", | |
| "language_model.model.layers.24.self_attn.q_proj", | |
| "language_model.model.layers.24.self_attn.k_proj", | |
| "language_model.model.layers.24.self_attn.v_proj", | |
| "language_model.model.layers.24.self_attn.o_proj", | |
| "language_model.model.layers.24.mlp.gate_proj", | |
| "language_model.model.layers.24.mlp.up_proj", | |
| "language_model.model.layers.24.mlp.down_proj", | |
| "language_model.model.layers.25.self_attn.q_proj", | |
| "language_model.model.layers.25.self_attn.k_proj", | |
| "language_model.model.layers.25.self_attn.v_proj", | |
| "language_model.model.layers.25.self_attn.o_proj", | |
| "language_model.model.layers.25.mlp.gate_proj", | |
| "language_model.model.layers.25.mlp.up_proj", | |
| "language_model.model.layers.25.mlp.down_proj", | |
| "language_model.model.layers.26.self_attn.q_proj", | |
| "language_model.model.layers.26.self_attn.k_proj", | |
| "language_model.model.layers.26.self_attn.v_proj", | |
| "language_model.model.layers.26.self_attn.o_proj", | |
| "language_model.model.layers.26.mlp.gate_proj", | |
| "language_model.model.layers.26.mlp.up_proj", | |
| "language_model.model.layers.26.mlp.down_proj", | |
| "language_model.model.layers.27.self_attn.q_proj", | |
| "language_model.model.layers.27.self_attn.k_proj", | |
| "language_model.model.layers.27.self_attn.v_proj", | |
| "language_model.model.layers.27.self_attn.o_proj", | |
| "language_model.model.layers.27.mlp.gate_proj", | |
| "language_model.model.layers.27.mlp.up_proj", | |
| "language_model.model.layers.27.mlp.down_proj", | |
| "language_model.model.layers.28.self_attn.q_proj", | |
| "language_model.model.layers.28.self_attn.k_proj", | |
| "language_model.model.layers.28.self_attn.v_proj", | |
| "language_model.model.layers.28.self_attn.o_proj", | |
| "language_model.model.layers.28.mlp.gate_proj", | |
| "language_model.model.layers.28.mlp.up_proj", | |
| "language_model.model.layers.28.mlp.down_proj", | |
| "language_model.model.layers.29.self_attn.q_proj", | |
| "language_model.model.layers.29.self_attn.k_proj", | |
| "language_model.model.layers.29.self_attn.v_proj", | |
| "language_model.model.layers.29.self_attn.o_proj", | |
| "language_model.model.layers.29.mlp.gate_proj", | |
| "language_model.model.layers.29.mlp.up_proj", | |
| "language_model.model.layers.29.mlp.down_proj", | |
| "language_model.model.layers.30.self_attn.q_proj", | |
| "language_model.model.layers.30.self_attn.k_proj", | |
| "language_model.model.layers.30.self_attn.v_proj", | |
| "language_model.model.layers.30.self_attn.o_proj", | |
| "language_model.model.layers.30.mlp.gate_proj", | |
| "language_model.model.layers.30.mlp.up_proj", | |
| "language_model.model.layers.30.mlp.down_proj", | |
| "language_model.model.layers.31.self_attn.q_proj", | |
| "language_model.model.layers.31.self_attn.k_proj", | |
| "language_model.model.layers.31.self_attn.v_proj", | |
| "language_model.model.layers.31.self_attn.o_proj", | |
| "language_model.model.layers.31.mlp.gate_proj", | |
| "language_model.model.layers.31.mlp.up_proj", | |
| "language_model.model.layers.31.mlp.down_proj", | |
| "language_model.model.layers.32.self_attn.q_proj", | |
| "language_model.model.layers.32.self_attn.k_proj", | |
| "language_model.model.layers.32.self_attn.v_proj", | |
| "language_model.model.layers.32.self_attn.o_proj", | |
| "language_model.model.layers.32.mlp.gate_proj", | |
| "language_model.model.layers.32.mlp.up_proj", | |
| "language_model.model.layers.32.mlp.down_proj", | |
| "language_model.model.layers.33.self_attn.q_proj", | |
| "language_model.model.layers.33.self_attn.k_proj", | |
| "language_model.model.layers.33.self_attn.v_proj", | |
| "language_model.model.layers.33.self_attn.o_proj", | |
| "language_model.model.layers.33.mlp.gate_proj", | |
| "language_model.model.layers.33.mlp.up_proj", | |
| "language_model.model.layers.33.mlp.down_proj", | |
| "language_model.model.layers.34.self_attn.q_proj", | |
| "language_model.model.layers.34.self_attn.k_proj", | |
| "language_model.model.layers.34.self_attn.v_proj", | |
| "language_model.model.layers.34.self_attn.o_proj", | |
| "language_model.model.layers.34.mlp.gate_proj", | |
| "language_model.model.layers.34.mlp.up_proj", | |
| "language_model.model.layers.34.mlp.down_proj", | |
| "language_model.model.layers.35.self_attn.q_proj", | |
| "language_model.model.layers.35.self_attn.k_proj", | |
| "language_model.model.layers.35.self_attn.v_proj", | |
| "language_model.model.layers.35.self_attn.o_proj", | |
| "language_model.model.layers.35.mlp.gate_proj", | |
| "language_model.model.layers.35.mlp.up_proj", | |
| "language_model.model.layers.35.mlp.down_proj", | |
| "language_model.model.layers.36.self_attn.q_proj", | |
| "language_model.model.layers.36.self_attn.k_proj", | |
| "language_model.model.layers.36.self_attn.v_proj", | |
| "language_model.model.layers.36.self_attn.o_proj", | |
| "language_model.model.layers.36.mlp.gate_proj", | |
| "language_model.model.layers.36.mlp.up_proj", | |
| "language_model.model.layers.36.mlp.down_proj", | |
| "language_model.model.layers.37.self_attn.q_proj", | |
| "language_model.model.layers.37.self_attn.k_proj", | |
| "language_model.model.layers.37.self_attn.v_proj", | |
| "language_model.model.layers.37.self_attn.o_proj", | |
| "language_model.model.layers.37.mlp.gate_proj", | |
| "language_model.model.layers.37.mlp.up_proj", | |
| "language_model.model.layers.37.mlp.down_proj", | |
| "language_model.model.layers.38.self_attn.q_proj", | |
| "language_model.model.layers.38.self_attn.k_proj", | |
| "language_model.model.layers.38.self_attn.v_proj", | |
| "language_model.model.layers.38.self_attn.o_proj", | |
| "language_model.model.layers.38.mlp.gate_proj", | |
| "language_model.model.layers.38.mlp.up_proj", | |
| "language_model.model.layers.38.mlp.down_proj", | |
| "language_model.model.layers.39.self_attn.q_proj", | |
| "language_model.model.layers.39.self_attn.k_proj", | |
| "language_model.model.layers.39.self_attn.v_proj", | |
| "language_model.model.layers.39.self_attn.o_proj", | |
| "language_model.model.layers.39.mlp.gate_proj", | |
| "language_model.model.layers.39.mlp.up_proj", | |
| "language_model.model.layers.39.mlp.down_proj", | |
| "language_model.model.layers.40.self_attn.q_proj", | |
| "language_model.model.layers.40.self_attn.k_proj", | |
| "language_model.model.layers.40.self_attn.v_proj", | |
| "language_model.model.layers.40.self_attn.o_proj", | |
| "language_model.model.layers.40.mlp.gate_proj", | |
| "language_model.model.layers.40.mlp.up_proj", | |
| "language_model.model.layers.40.mlp.down_proj", | |
| "language_model.model.layers.41.self_attn.q_proj", | |
| "language_model.model.layers.41.self_attn.k_proj", | |
| "language_model.model.layers.41.self_attn.v_proj", | |
| "language_model.model.layers.41.self_attn.o_proj", | |
| "language_model.model.layers.41.mlp.gate_proj", | |
| "language_model.model.layers.41.mlp.up_proj", | |
| "language_model.model.layers.41.mlp.down_proj", | |
| "language_model.model.layers.42.self_attn.q_proj", | |
| "language_model.model.layers.42.self_attn.k_proj", | |
| "language_model.model.layers.42.self_attn.v_proj", | |
| "language_model.model.layers.42.self_attn.o_proj", | |
| "language_model.model.layers.42.mlp.gate_proj", | |
| "language_model.model.layers.42.mlp.up_proj", | |
| "language_model.model.layers.42.mlp.down_proj", | |
| "language_model.model.layers.43.self_attn.q_proj", | |
| "language_model.model.layers.43.self_attn.k_proj", | |
| "language_model.model.layers.43.self_attn.v_proj", | |
| "language_model.model.layers.43.self_attn.o_proj", | |
| "language_model.model.layers.43.mlp.gate_proj", | |
| "language_model.model.layers.43.mlp.up_proj", | |
| "language_model.model.layers.43.mlp.down_proj", | |
| "language_model.model.layers.44.self_attn.q_proj", | |
| "language_model.model.layers.44.self_attn.k_proj", | |
| "language_model.model.layers.44.self_attn.v_proj", | |
| "language_model.model.layers.44.self_attn.o_proj", | |
| "language_model.model.layers.44.mlp.gate_proj", | |
| "language_model.model.layers.44.mlp.up_proj", | |
| "language_model.model.layers.44.mlp.down_proj", | |
| "language_model.model.layers.45.self_attn.q_proj", | |
| "language_model.model.layers.45.self_attn.k_proj", | |
| "language_model.model.layers.45.self_attn.v_proj", | |
| "language_model.model.layers.45.self_attn.o_proj", | |
| "language_model.model.layers.45.mlp.gate_proj", | |
| "language_model.model.layers.45.mlp.up_proj", | |
| "language_model.model.layers.45.mlp.down_proj", | |
| "language_model.model.layers.46.self_attn.q_proj", | |
| "language_model.model.layers.46.self_attn.k_proj", | |
| "language_model.model.layers.46.self_attn.v_proj", | |
| "language_model.model.layers.46.self_attn.o_proj", | |
| "language_model.model.layers.46.mlp.gate_proj", | |
| "language_model.model.layers.46.mlp.up_proj", | |
| "language_model.model.layers.46.mlp.down_proj", | |
| "language_model.model.layers.47.self_attn.q_proj", | |
| "language_model.model.layers.47.self_attn.k_proj", | |
| "language_model.model.layers.47.self_attn.v_proj", | |
| "language_model.model.layers.47.self_attn.o_proj", | |
| "language_model.model.layers.47.mlp.gate_proj", | |
| "language_model.model.layers.47.mlp.up_proj", | |
| "language_model.model.layers.47.mlp.down_proj", | |
| "language_model.model.layers.48.self_attn.q_proj", | |
| "language_model.model.layers.48.self_attn.k_proj", | |
| "language_model.model.layers.48.self_attn.v_proj", | |
| "language_model.model.layers.48.self_attn.o_proj", | |
| "language_model.model.layers.48.mlp.gate_proj", | |
| "language_model.model.layers.48.mlp.up_proj", | |
| "language_model.model.layers.48.mlp.down_proj", | |
| "language_model.model.layers.49.self_attn.q_proj", | |
| "language_model.model.layers.49.self_attn.k_proj", | |
| "language_model.model.layers.49.self_attn.v_proj", | |
| "language_model.model.layers.49.self_attn.o_proj", | |
| "language_model.model.layers.49.mlp.gate_proj", | |
| "language_model.model.layers.49.mlp.up_proj", | |
| "language_model.model.layers.49.mlp.down_proj", | |
| "language_model.model.layers.50.self_attn.q_proj", | |
| "language_model.model.layers.50.self_attn.k_proj", | |
| "language_model.model.layers.50.self_attn.v_proj", | |
| "language_model.model.layers.50.self_attn.o_proj", | |
| "language_model.model.layers.50.mlp.gate_proj", | |
| "language_model.model.layers.50.mlp.up_proj", | |
| "language_model.model.layers.50.mlp.down_proj", | |
| "language_model.model.layers.51.self_attn.q_proj", | |
| "language_model.model.layers.51.self_attn.k_proj", | |
| "language_model.model.layers.51.self_attn.v_proj", | |
| "language_model.model.layers.51.self_attn.o_proj", | |
| "language_model.model.layers.51.mlp.gate_proj", | |
| "language_model.model.layers.51.mlp.up_proj", | |
| "language_model.model.layers.51.mlp.down_proj", | |
| "language_model.model.layers.52.self_attn.q_proj", | |
| "language_model.model.layers.52.self_attn.k_proj", | |
| "language_model.model.layers.52.self_attn.v_proj", | |
| "language_model.model.layers.52.self_attn.o_proj", | |
| "language_model.model.layers.52.mlp.gate_proj", | |
| "language_model.model.layers.52.mlp.up_proj", | |
| "language_model.model.layers.52.mlp.down_proj", | |
| "language_model.model.layers.53.self_attn.q_proj", | |
| "language_model.model.layers.53.self_attn.k_proj", | |
| "language_model.model.layers.53.self_attn.v_proj", | |
| "language_model.model.layers.53.self_attn.o_proj", | |
| "language_model.model.layers.53.mlp.gate_proj", | |
| "language_model.model.layers.53.mlp.up_proj", | |
| "language_model.model.layers.53.mlp.down_proj", | |
| "language_model.model.layers.54.self_attn.q_proj", | |
| "language_model.model.layers.54.self_attn.k_proj", | |
| "language_model.model.layers.54.self_attn.v_proj", | |
| "language_model.model.layers.54.self_attn.o_proj", | |
| "language_model.model.layers.54.mlp.gate_proj", | |
| "language_model.model.layers.54.mlp.up_proj", | |
| "language_model.model.layers.54.mlp.down_proj", | |
| "language_model.model.layers.55.self_attn.q_proj", | |
| "language_model.model.layers.55.self_attn.k_proj", | |
| "language_model.model.layers.55.self_attn.v_proj", | |
| "language_model.model.layers.55.self_attn.o_proj", | |
| "language_model.model.layers.55.mlp.gate_proj", | |
| "language_model.model.layers.55.mlp.up_proj", | |
| "language_model.model.layers.55.mlp.down_proj", | |
| "language_model.model.layers.56.self_attn.q_proj", | |
| "language_model.model.layers.56.self_attn.k_proj", | |
| "language_model.model.layers.56.self_attn.v_proj", | |
| "language_model.model.layers.56.self_attn.o_proj", | |
| "language_model.model.layers.56.mlp.gate_proj", | |
| "language_model.model.layers.56.mlp.up_proj", | |
| "language_model.model.layers.56.mlp.down_proj", | |
| "language_model.model.layers.57.self_attn.q_proj", | |
| "language_model.model.layers.57.self_attn.k_proj", | |
| "language_model.model.layers.57.self_attn.v_proj", | |
| "language_model.model.layers.57.self_attn.o_proj", | |
| "language_model.model.layers.57.mlp.gate_proj", | |
| "language_model.model.layers.57.mlp.up_proj", | |
| "language_model.model.layers.57.mlp.down_proj", | |
| "language_model.model.layers.58.self_attn.q_proj", | |
| "language_model.model.layers.58.self_attn.k_proj", | |
| "language_model.model.layers.58.self_attn.v_proj", | |
| "language_model.model.layers.58.self_attn.o_proj", | |
| "language_model.model.layers.58.mlp.gate_proj", | |
| "language_model.model.layers.58.mlp.up_proj", | |
| "language_model.model.layers.58.mlp.down_proj", | |
| "language_model.model.layers.59.self_attn.q_proj", | |
| "language_model.model.layers.59.self_attn.k_proj", | |
| "language_model.model.layers.59.self_attn.v_proj", | |
| "language_model.model.layers.59.self_attn.o_proj", | |
| "language_model.model.layers.59.mlp.gate_proj", | |
| "language_model.model.layers.59.mlp.up_proj", | |
| "language_model.model.layers.59.mlp.down_proj", | |
| "language_model.model.layers.60.self_attn.q_proj", | |
| "language_model.model.layers.60.self_attn.k_proj", | |
| "language_model.model.layers.60.self_attn.v_proj", | |
| "language_model.model.layers.60.self_attn.o_proj", | |
| "language_model.model.layers.60.mlp.gate_proj", | |
| "language_model.model.layers.60.mlp.up_proj", | |
| "language_model.model.layers.60.mlp.down_proj", | |
| "language_model.model.layers.61.self_attn.q_proj", | |
| "language_model.model.layers.61.self_attn.k_proj", | |
| "language_model.model.layers.61.self_attn.v_proj", | |
| "language_model.model.layers.61.self_attn.o_proj", | |
| "language_model.model.layers.61.mlp.gate_proj", | |
| "language_model.model.layers.61.mlp.up_proj", | |
| "language_model.model.layers.61.mlp.down_proj", | |
| "language_model.model.layers.62.self_attn.q_proj", | |
| "language_model.model.layers.62.self_attn.k_proj", | |
| "language_model.model.layers.62.self_attn.v_proj", | |
| "language_model.model.layers.62.self_attn.o_proj", | |
| "language_model.model.layers.62.mlp.gate_proj", | |
| "language_model.model.layers.62.mlp.up_proj", | |
| "language_model.model.layers.62.mlp.down_proj", | |
| "language_model.model.layers.63.self_attn.q_proj", | |
| "language_model.model.layers.63.self_attn.k_proj", | |
| "language_model.model.layers.63.self_attn.v_proj", | |
| "language_model.model.layers.63.self_attn.o_proj", | |
| "language_model.model.layers.63.mlp.gate_proj", | |
| "language_model.model.layers.63.mlp.up_proj", | |
| "language_model.model.layers.63.mlp.down_proj", | |
| "language_model.model.layers.64.self_attn.q_proj", | |
| "language_model.model.layers.64.self_attn.k_proj", | |
| "language_model.model.layers.64.self_attn.v_proj", | |
| "language_model.model.layers.64.self_attn.o_proj", | |
| "language_model.model.layers.64.mlp.gate_proj", | |
| "language_model.model.layers.64.mlp.up_proj", | |
| "language_model.model.layers.64.mlp.down_proj", | |
| "language_model.model.layers.65.self_attn.q_proj", | |
| "language_model.model.layers.65.self_attn.k_proj", | |
| "language_model.model.layers.65.self_attn.v_proj", | |
| "language_model.model.layers.65.self_attn.o_proj", | |
| "language_model.model.layers.65.mlp.gate_proj", | |
| "language_model.model.layers.65.mlp.up_proj", | |
| "language_model.model.layers.65.mlp.down_proj", | |
| "language_model.model.layers.66.self_attn.q_proj", | |
| "language_model.model.layers.66.self_attn.k_proj", | |
| "language_model.model.layers.66.self_attn.v_proj", | |
| "language_model.model.layers.66.self_attn.o_proj", | |
| "language_model.model.layers.66.mlp.gate_proj", | |
| "language_model.model.layers.66.mlp.up_proj", | |
| "language_model.model.layers.66.mlp.down_proj", | |
| "language_model.model.layers.67.self_attn.q_proj", | |
| "language_model.model.layers.67.self_attn.k_proj", | |
| "language_model.model.layers.67.self_attn.v_proj", | |
| "language_model.model.layers.67.self_attn.o_proj", | |
| "language_model.model.layers.67.mlp.gate_proj", | |
| "language_model.model.layers.67.mlp.up_proj", | |
| "language_model.model.layers.67.mlp.down_proj", | |
| "language_model.model.layers.68.self_attn.q_proj", | |
| "language_model.model.layers.68.self_attn.k_proj", | |
| "language_model.model.layers.68.self_attn.v_proj", | |
| "language_model.model.layers.68.self_attn.o_proj", | |
| "language_model.model.layers.68.mlp.gate_proj", | |
| "language_model.model.layers.68.mlp.up_proj", | |
| "language_model.model.layers.68.mlp.down_proj", | |
| "language_model.model.layers.69.self_attn.q_proj", | |
| "language_model.model.layers.69.self_attn.k_proj", | |
| "language_model.model.layers.69.self_attn.v_proj", | |
| "language_model.model.layers.69.self_attn.o_proj", | |
| "language_model.model.layers.69.mlp.gate_proj", | |
| "language_model.model.layers.69.mlp.up_proj", | |
| "language_model.model.layers.69.mlp.down_proj", | |
| "language_model.model.layers.70.self_attn.q_proj", | |
| "language_model.model.layers.70.self_attn.k_proj", | |
| "language_model.model.layers.70.self_attn.v_proj", | |
| "language_model.model.layers.70.self_attn.o_proj", | |
| "language_model.model.layers.70.mlp.gate_proj", | |
| "language_model.model.layers.70.mlp.up_proj", | |
| "language_model.model.layers.70.mlp.down_proj", | |
| "language_model.model.layers.71.self_attn.q_proj", | |
| "language_model.model.layers.71.self_attn.k_proj", | |
| "language_model.model.layers.71.self_attn.v_proj", | |
| "language_model.model.layers.71.self_attn.o_proj", | |
| "language_model.model.layers.71.mlp.gate_proj", | |
| "language_model.model.layers.71.mlp.up_proj", | |
| "language_model.model.layers.71.mlp.down_proj", | |
| "language_model.model.layers.72.self_attn.q_proj", | |
| "language_model.model.layers.72.self_attn.k_proj", | |
| "language_model.model.layers.72.self_attn.v_proj", | |
| "language_model.model.layers.72.self_attn.o_proj", | |
| "language_model.model.layers.72.mlp.gate_proj", | |
| "language_model.model.layers.72.mlp.up_proj", | |
| "language_model.model.layers.72.mlp.down_proj", | |
| "language_model.model.layers.73.self_attn.q_proj", | |
| "language_model.model.layers.73.self_attn.k_proj", | |
| "language_model.model.layers.73.self_attn.v_proj", | |
| "language_model.model.layers.73.self_attn.o_proj", | |
| "language_model.model.layers.73.mlp.gate_proj", | |
| "language_model.model.layers.73.mlp.up_proj", | |
| "language_model.model.layers.73.mlp.down_proj", | |
| "language_model.model.layers.74.self_attn.q_proj", | |
| "language_model.model.layers.74.self_attn.k_proj", | |
| "language_model.model.layers.74.self_attn.v_proj", | |
| "language_model.model.layers.74.self_attn.o_proj", | |
| "language_model.model.layers.74.mlp.gate_proj", | |
| "language_model.model.layers.74.mlp.up_proj", | |
| "language_model.model.layers.74.mlp.down_proj", | |
| "language_model.model.layers.75.self_attn.q_proj", | |
| "language_model.model.layers.75.self_attn.k_proj", | |
| "language_model.model.layers.75.self_attn.v_proj", | |
| "language_model.model.layers.75.self_attn.o_proj", | |
| "language_model.model.layers.75.mlp.gate_proj", | |
| "language_model.model.layers.75.mlp.up_proj", | |
| "language_model.model.layers.75.mlp.down_proj", | |
| "language_model.model.layers.76.self_attn.q_proj", | |
| "language_model.model.layers.76.self_attn.k_proj", | |
| "language_model.model.layers.76.self_attn.v_proj", | |
| "language_model.model.layers.76.self_attn.o_proj", | |
| "language_model.model.layers.76.mlp.gate_proj", | |
| "language_model.model.layers.76.mlp.up_proj", | |
| "language_model.model.layers.76.mlp.down_proj", | |
| "language_model.model.layers.77.self_attn.q_proj", | |
| "language_model.model.layers.77.self_attn.k_proj", | |
| "language_model.model.layers.77.self_attn.v_proj", | |
| "language_model.model.layers.77.self_attn.o_proj", | |
| "language_model.model.layers.77.mlp.gate_proj", | |
| "language_model.model.layers.77.mlp.up_proj", | |
| "language_model.model.layers.77.mlp.down_proj", | |
| "language_model.model.layers.78.self_attn.q_proj", | |
| "language_model.model.layers.78.self_attn.k_proj", | |
| "language_model.model.layers.78.self_attn.v_proj", | |
| "language_model.model.layers.78.self_attn.o_proj", | |
| "language_model.model.layers.78.mlp.gate_proj", | |
| "language_model.model.layers.78.mlp.up_proj", | |
| "language_model.model.layers.78.mlp.down_proj", | |
| "language_model.model.layers.79.self_attn.q_proj", | |
| "language_model.model.layers.79.self_attn.k_proj", | |
| "language_model.model.layers.79.self_attn.v_proj", | |
| "language_model.model.layers.79.self_attn.o_proj", | |
| "language_model.model.layers.79.mlp.gate_proj", | |
| "language_model.model.layers.79.mlp.up_proj", | |
| "language_model.model.layers.79.mlp.down_proj", | |
| "language_model.model.layers.80.self_attn.q_proj", | |
| "language_model.model.layers.80.self_attn.k_proj", | |
| "language_model.model.layers.80.self_attn.v_proj", | |
| "language_model.model.layers.80.self_attn.o_proj", | |
| "language_model.model.layers.80.mlp.gate_proj", | |
| "language_model.model.layers.80.mlp.up_proj", | |
| "language_model.model.layers.80.mlp.down_proj", | |
| "language_model.model.layers.81.self_attn.q_proj", | |
| "language_model.model.layers.81.self_attn.k_proj", | |
| "language_model.model.layers.81.self_attn.v_proj", | |
| "language_model.model.layers.81.self_attn.o_proj", | |
| "language_model.model.layers.81.mlp.gate_proj", | |
| "language_model.model.layers.81.mlp.up_proj", | |
| "language_model.model.layers.81.mlp.down_proj", | |
| "language_model.model.layers.82.self_attn.q_proj", | |
| "language_model.model.layers.82.self_attn.k_proj", | |
| "language_model.model.layers.82.self_attn.v_proj", | |
| "language_model.model.layers.82.self_attn.o_proj", | |
| "language_model.model.layers.82.mlp.gate_proj", | |
| "language_model.model.layers.82.mlp.up_proj", | |
| "language_model.model.layers.82.mlp.down_proj", | |
| "language_model.model.layers.83.self_attn.q_proj", | |
| "language_model.model.layers.83.self_attn.k_proj", | |
| "language_model.model.layers.83.self_attn.v_proj", | |
| "language_model.model.layers.83.self_attn.o_proj", | |
| "language_model.model.layers.83.mlp.gate_proj", | |
| "language_model.model.layers.83.mlp.up_proj", | |
| "language_model.model.layers.83.mlp.down_proj", | |
| "language_model.model.layers.84.self_attn.q_proj", | |
| "language_model.model.layers.84.self_attn.k_proj", | |
| "language_model.model.layers.84.self_attn.v_proj", | |
| "language_model.model.layers.84.self_attn.o_proj", | |
| "language_model.model.layers.84.mlp.gate_proj", | |
| "language_model.model.layers.84.mlp.up_proj", | |
| "language_model.model.layers.84.mlp.down_proj", | |
| "language_model.model.layers.85.self_attn.q_proj", | |
| "language_model.model.layers.85.self_attn.k_proj", | |
| "language_model.model.layers.85.self_attn.v_proj", | |
| "language_model.model.layers.85.self_attn.o_proj", | |
| "language_model.model.layers.85.mlp.gate_proj", | |
| "language_model.model.layers.85.mlp.up_proj", | |
| "language_model.model.layers.85.mlp.down_proj", | |
| "language_model.model.layers.86.self_attn.q_proj", | |
| "language_model.model.layers.86.self_attn.k_proj", | |
| "language_model.model.layers.86.self_attn.v_proj", | |
| "language_model.model.layers.86.self_attn.o_proj", | |
| "language_model.model.layers.86.mlp.gate_proj", | |
| "language_model.model.layers.86.mlp.up_proj", | |
| "language_model.model.layers.86.mlp.down_proj", | |
| "language_model.model.layers.87.self_attn.q_proj", | |
| "language_model.model.layers.87.self_attn.k_proj", | |
| "language_model.model.layers.87.self_attn.v_proj", | |
| "language_model.model.layers.87.self_attn.o_proj", | |
| "language_model.model.layers.87.mlp.gate_proj", | |
| "language_model.model.layers.87.mlp.up_proj", | |
| "language_model.model.layers.87.mlp.down_proj", | |
| "language_model.lm_head" | |
| ], | |
| "registry_requires_subclass": false, | |
| "sparsity_structure": "unstructured", | |
| "targets": [ | |
| "language_model.model.layers.0.self_attn.q_proj", | |
| "language_model.model.layers.0.self_attn.k_proj" | |
| ] | |
| } | |
| }, | |
| "text_config": { | |
| "hidden_size": 12288, | |
| "intermediate_size": 28672, | |
| "is_composition": true, | |
| "max_position_embeddings": 131072, | |
| "model_type": "mistral", | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 96, | |
| "num_hidden_layers": 88, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000000.0, | |
| "sliding_window": null, | |
| "vocab_size": 32768 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.3", | |
| "vision_config": { | |
| "head_dim": 88, | |
| "hidden_act": "silu", | |
| "hidden_size": 1408, | |
| "image_break_token_id": 14, | |
| "image_end_token_id": 15, | |
| "image_size": 1024, | |
| "image_token_id": 10, | |
| "intermediate_size": 6144, | |
| "model_type": "pixtral", | |
| "num_hidden_layers": 40, | |
| "patch_size": 16, | |
| "rope_theta": 10000.0 | |
| }, | |
| "vision_feature_layer": -1, | |
| "vision_feature_select_strategy": "full" | |
| } |