llama3.2-quantised / config.json
developer-314e's picture
Upload MllamaForConditionalGeneration
5c1fa39 verified
{
"_name_or_path": "Llama-3.2-11B-Vision-Instruct-W4A16-G128",
"architectures": [
"MllamaForConditionalGeneration"
],
"image_token_index": 128256,
"model_type": "mllama",
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": null,
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": null,
"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": 1.363428206546751,
"ignore": [
"vision_model.transformer.layers.0.self_attn.q_proj",
"vision_model.transformer.layers.0.self_attn.k_proj",
"vision_model.transformer.layers.0.self_attn.v_proj",
"vision_model.transformer.layers.0.self_attn.o_proj",
"vision_model.transformer.layers.0.mlp.fc1",
"vision_model.transformer.layers.0.mlp.fc2",
"vision_model.transformer.layers.1.self_attn.q_proj",
"vision_model.transformer.layers.1.self_attn.k_proj",
"vision_model.transformer.layers.1.self_attn.v_proj",
"vision_model.transformer.layers.1.self_attn.o_proj",
"vision_model.transformer.layers.1.mlp.fc1",
"vision_model.transformer.layers.1.mlp.fc2",
"vision_model.transformer.layers.2.self_attn.q_proj",
"vision_model.transformer.layers.2.self_attn.k_proj",
"vision_model.transformer.layers.2.self_attn.v_proj",
"vision_model.transformer.layers.2.self_attn.o_proj",
"vision_model.transformer.layers.2.mlp.fc1",
"vision_model.transformer.layers.2.mlp.fc2",
"vision_model.transformer.layers.3.self_attn.q_proj",
"vision_model.transformer.layers.3.self_attn.k_proj",
"vision_model.transformer.layers.3.self_attn.v_proj",
"vision_model.transformer.layers.3.self_attn.o_proj",
"vision_model.transformer.layers.3.mlp.fc1",
"vision_model.transformer.layers.3.mlp.fc2",
"vision_model.transformer.layers.4.self_attn.q_proj",
"vision_model.transformer.layers.4.self_attn.k_proj",
"vision_model.transformer.layers.4.self_attn.v_proj",
"vision_model.transformer.layers.4.self_attn.o_proj",
"vision_model.transformer.layers.4.mlp.fc1",
"vision_model.transformer.layers.4.mlp.fc2",
"vision_model.transformer.layers.5.self_attn.q_proj",
"vision_model.transformer.layers.5.self_attn.k_proj",
"vision_model.transformer.layers.5.self_attn.v_proj",
"vision_model.transformer.layers.5.self_attn.o_proj",
"vision_model.transformer.layers.5.mlp.fc1",
"vision_model.transformer.layers.5.mlp.fc2",
"vision_model.transformer.layers.6.self_attn.q_proj",
"vision_model.transformer.layers.6.self_attn.k_proj",
"vision_model.transformer.layers.6.self_attn.v_proj",
"vision_model.transformer.layers.6.self_attn.o_proj",
"vision_model.transformer.layers.6.mlp.fc1",
"vision_model.transformer.layers.6.mlp.fc2",
"vision_model.transformer.layers.7.self_attn.q_proj",
"vision_model.transformer.layers.7.self_attn.k_proj",
"vision_model.transformer.layers.7.self_attn.v_proj",
"vision_model.transformer.layers.7.self_attn.o_proj",
"vision_model.transformer.layers.7.mlp.fc1",
"vision_model.transformer.layers.7.mlp.fc2",
"vision_model.transformer.layers.8.self_attn.q_proj",
"vision_model.transformer.layers.8.self_attn.k_proj",
"vision_model.transformer.layers.8.self_attn.v_proj",
"vision_model.transformer.layers.8.self_attn.o_proj",
"vision_model.transformer.layers.8.mlp.fc1",
"vision_model.transformer.layers.8.mlp.fc2",
"vision_model.transformer.layers.9.self_attn.q_proj",
"vision_model.transformer.layers.9.self_attn.k_proj",
"vision_model.transformer.layers.9.self_attn.v_proj",
"vision_model.transformer.layers.9.self_attn.o_proj",
"vision_model.transformer.layers.9.mlp.fc1",
"vision_model.transformer.layers.9.mlp.fc2",
"vision_model.transformer.layers.10.self_attn.q_proj",
"vision_model.transformer.layers.10.self_attn.k_proj",
"vision_model.transformer.layers.10.self_attn.v_proj",
"vision_model.transformer.layers.10.self_attn.o_proj",
"vision_model.transformer.layers.10.mlp.fc1",
"vision_model.transformer.layers.10.mlp.fc2",
"vision_model.transformer.layers.11.self_attn.q_proj",
"vision_model.transformer.layers.11.self_attn.k_proj",
"vision_model.transformer.layers.11.self_attn.v_proj",
"vision_model.transformer.layers.11.self_attn.o_proj",
"vision_model.transformer.layers.11.mlp.fc1",
"vision_model.transformer.layers.11.mlp.fc2",
"vision_model.transformer.layers.12.self_attn.q_proj",
"vision_model.transformer.layers.12.self_attn.k_proj",
"vision_model.transformer.layers.12.self_attn.v_proj",
"vision_model.transformer.layers.12.self_attn.o_proj",
"vision_model.transformer.layers.12.mlp.fc1",
"vision_model.transformer.layers.12.mlp.fc2",
"vision_model.transformer.layers.13.self_attn.q_proj",
"vision_model.transformer.layers.13.self_attn.k_proj",
"vision_model.transformer.layers.13.self_attn.v_proj",
"vision_model.transformer.layers.13.self_attn.o_proj",
"vision_model.transformer.layers.13.mlp.fc1",
"vision_model.transformer.layers.13.mlp.fc2",
"vision_model.transformer.layers.14.self_attn.q_proj",
"vision_model.transformer.layers.14.self_attn.k_proj",
"vision_model.transformer.layers.14.self_attn.v_proj",
"vision_model.transformer.layers.14.self_attn.o_proj",
"vision_model.transformer.layers.14.mlp.fc1",
"vision_model.transformer.layers.14.mlp.fc2",
"vision_model.transformer.layers.15.self_attn.q_proj",
"vision_model.transformer.layers.15.self_attn.k_proj",
"vision_model.transformer.layers.15.self_attn.v_proj",
"vision_model.transformer.layers.15.self_attn.o_proj",
"vision_model.transformer.layers.15.mlp.fc1",
"vision_model.transformer.layers.15.mlp.fc2",
"vision_model.transformer.layers.16.self_attn.q_proj",
"vision_model.transformer.layers.16.self_attn.k_proj",
"vision_model.transformer.layers.16.self_attn.v_proj",
"vision_model.transformer.layers.16.self_attn.o_proj",
"vision_model.transformer.layers.16.mlp.fc1",
"vision_model.transformer.layers.16.mlp.fc2",
"vision_model.transformer.layers.17.self_attn.q_proj",
"vision_model.transformer.layers.17.self_attn.k_proj",
"vision_model.transformer.layers.17.self_attn.v_proj",
"vision_model.transformer.layers.17.self_attn.o_proj",
"vision_model.transformer.layers.17.mlp.fc1",
"vision_model.transformer.layers.17.mlp.fc2",
"vision_model.transformer.layers.18.self_attn.q_proj",
"vision_model.transformer.layers.18.self_attn.k_proj",
"vision_model.transformer.layers.18.self_attn.v_proj",
"vision_model.transformer.layers.18.self_attn.o_proj",
"vision_model.transformer.layers.18.mlp.fc1",
"vision_model.transformer.layers.18.mlp.fc2",
"vision_model.transformer.layers.19.self_attn.q_proj",
"vision_model.transformer.layers.19.self_attn.k_proj",
"vision_model.transformer.layers.19.self_attn.v_proj",
"vision_model.transformer.layers.19.self_attn.o_proj",
"vision_model.transformer.layers.19.mlp.fc1",
"vision_model.transformer.layers.19.mlp.fc2",
"vision_model.transformer.layers.20.self_attn.q_proj",
"vision_model.transformer.layers.20.self_attn.k_proj",
"vision_model.transformer.layers.20.self_attn.v_proj",
"vision_model.transformer.layers.20.self_attn.o_proj",
"vision_model.transformer.layers.20.mlp.fc1",
"vision_model.transformer.layers.20.mlp.fc2",
"vision_model.transformer.layers.21.self_attn.q_proj",
"vision_model.transformer.layers.21.self_attn.k_proj",
"vision_model.transformer.layers.21.self_attn.v_proj",
"vision_model.transformer.layers.21.self_attn.o_proj",
"vision_model.transformer.layers.21.mlp.fc1",
"vision_model.transformer.layers.21.mlp.fc2",
"vision_model.transformer.layers.22.self_attn.q_proj",
"vision_model.transformer.layers.22.self_attn.k_proj",
"vision_model.transformer.layers.22.self_attn.v_proj",
"vision_model.transformer.layers.22.self_attn.o_proj",
"vision_model.transformer.layers.22.mlp.fc1",
"vision_model.transformer.layers.22.mlp.fc2",
"vision_model.transformer.layers.23.self_attn.q_proj",
"vision_model.transformer.layers.23.self_attn.k_proj",
"vision_model.transformer.layers.23.self_attn.v_proj",
"vision_model.transformer.layers.23.self_attn.o_proj",
"vision_model.transformer.layers.23.mlp.fc1",
"vision_model.transformer.layers.23.mlp.fc2",
"vision_model.transformer.layers.24.self_attn.q_proj",
"vision_model.transformer.layers.24.self_attn.k_proj",
"vision_model.transformer.layers.24.self_attn.v_proj",
"vision_model.transformer.layers.24.self_attn.o_proj",
"vision_model.transformer.layers.24.mlp.fc1",
"vision_model.transformer.layers.24.mlp.fc2",
"vision_model.transformer.layers.25.self_attn.q_proj",
"vision_model.transformer.layers.25.self_attn.k_proj",
"vision_model.transformer.layers.25.self_attn.v_proj",
"vision_model.transformer.layers.25.self_attn.o_proj",
"vision_model.transformer.layers.25.mlp.fc1",
"vision_model.transformer.layers.25.mlp.fc2",
"vision_model.transformer.layers.26.self_attn.q_proj",
"vision_model.transformer.layers.26.self_attn.k_proj",
"vision_model.transformer.layers.26.self_attn.v_proj",
"vision_model.transformer.layers.26.self_attn.o_proj",
"vision_model.transformer.layers.26.mlp.fc1",
"vision_model.transformer.layers.26.mlp.fc2",
"vision_model.transformer.layers.27.self_attn.q_proj",
"vision_model.transformer.layers.27.self_attn.k_proj",
"vision_model.transformer.layers.27.self_attn.v_proj",
"vision_model.transformer.layers.27.self_attn.o_proj",
"vision_model.transformer.layers.27.mlp.fc1",
"vision_model.transformer.layers.27.mlp.fc2",
"vision_model.transformer.layers.28.self_attn.q_proj",
"vision_model.transformer.layers.28.self_attn.k_proj",
"vision_model.transformer.layers.28.self_attn.v_proj",
"vision_model.transformer.layers.28.self_attn.o_proj",
"vision_model.transformer.layers.28.mlp.fc1",
"vision_model.transformer.layers.28.mlp.fc2",
"vision_model.transformer.layers.29.self_attn.q_proj",
"vision_model.transformer.layers.29.self_attn.k_proj",
"vision_model.transformer.layers.29.self_attn.v_proj",
"vision_model.transformer.layers.29.self_attn.o_proj",
"vision_model.transformer.layers.29.mlp.fc1",
"vision_model.transformer.layers.29.mlp.fc2",
"vision_model.transformer.layers.30.self_attn.q_proj",
"vision_model.transformer.layers.30.self_attn.k_proj",
"vision_model.transformer.layers.30.self_attn.v_proj",
"vision_model.transformer.layers.30.self_attn.o_proj",
"vision_model.transformer.layers.30.mlp.fc1",
"vision_model.transformer.layers.30.mlp.fc2",
"vision_model.transformer.layers.31.self_attn.q_proj",
"vision_model.transformer.layers.31.self_attn.k_proj",
"vision_model.transformer.layers.31.self_attn.v_proj",
"vision_model.transformer.layers.31.self_attn.o_proj",
"vision_model.transformer.layers.31.mlp.fc1",
"vision_model.transformer.layers.31.mlp.fc2",
"vision_model.global_transformer.layers.0.self_attn.q_proj",
"vision_model.global_transformer.layers.0.self_attn.k_proj",
"vision_model.global_transformer.layers.0.self_attn.v_proj",
"vision_model.global_transformer.layers.0.self_attn.o_proj",
"vision_model.global_transformer.layers.0.mlp.fc1",
"vision_model.global_transformer.layers.0.mlp.fc2",
"vision_model.global_transformer.layers.1.self_attn.q_proj",
"vision_model.global_transformer.layers.1.self_attn.k_proj",
"vision_model.global_transformer.layers.1.self_attn.v_proj",
"vision_model.global_transformer.layers.1.self_attn.o_proj",
"vision_model.global_transformer.layers.1.mlp.fc1",
"vision_model.global_transformer.layers.1.mlp.fc2",
"vision_model.global_transformer.layers.2.self_attn.q_proj",
"vision_model.global_transformer.layers.2.self_attn.k_proj",
"vision_model.global_transformer.layers.2.self_attn.v_proj",
"vision_model.global_transformer.layers.2.self_attn.o_proj",
"vision_model.global_transformer.layers.2.mlp.fc1",
"vision_model.global_transformer.layers.2.mlp.fc2",
"vision_model.global_transformer.layers.3.self_attn.q_proj",
"vision_model.global_transformer.layers.3.self_attn.k_proj",
"vision_model.global_transformer.layers.3.self_attn.v_proj",
"vision_model.global_transformer.layers.3.self_attn.o_proj",
"vision_model.global_transformer.layers.3.mlp.fc1",
"vision_model.global_transformer.layers.3.mlp.fc2",
"vision_model.global_transformer.layers.4.self_attn.q_proj",
"vision_model.global_transformer.layers.4.self_attn.k_proj",
"vision_model.global_transformer.layers.4.self_attn.v_proj",
"vision_model.global_transformer.layers.4.self_attn.o_proj",
"vision_model.global_transformer.layers.4.mlp.fc1",
"vision_model.global_transformer.layers.4.mlp.fc2",
"vision_model.global_transformer.layers.5.self_attn.q_proj",
"vision_model.global_transformer.layers.5.self_attn.k_proj",
"vision_model.global_transformer.layers.5.self_attn.v_proj",
"vision_model.global_transformer.layers.5.self_attn.o_proj",
"vision_model.global_transformer.layers.5.mlp.fc1",
"vision_model.global_transformer.layers.5.mlp.fc2",
"vision_model.global_transformer.layers.6.self_attn.q_proj",
"vision_model.global_transformer.layers.6.self_attn.k_proj",
"vision_model.global_transformer.layers.6.self_attn.v_proj",
"vision_model.global_transformer.layers.6.self_attn.o_proj",
"vision_model.global_transformer.layers.6.mlp.fc1",
"vision_model.global_transformer.layers.6.mlp.fc2",
"vision_model.global_transformer.layers.7.self_attn.q_proj",
"vision_model.global_transformer.layers.7.self_attn.k_proj",
"vision_model.global_transformer.layers.7.self_attn.v_proj",
"vision_model.global_transformer.layers.7.self_attn.o_proj",
"vision_model.global_transformer.layers.7.mlp.fc1",
"vision_model.global_transformer.layers.7.mlp.fc2",
"language_model.lm_head",
"multi_modal_projector"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {
"format": "dense",
"global_sparsity": 0.13409465208989965,
"ignore": [
"vision_model.transformer.layers.0.self_attn.q_proj",
"vision_model.transformer.layers.0.self_attn.k_proj",
"vision_model.transformer.layers.0.self_attn.v_proj",
"vision_model.transformer.layers.0.self_attn.o_proj",
"vision_model.transformer.layers.0.mlp.fc1",
"vision_model.transformer.layers.0.mlp.fc2",
"vision_model.transformer.layers.1.self_attn.q_proj",
"vision_model.transformer.layers.1.self_attn.k_proj",
"vision_model.transformer.layers.1.self_attn.v_proj",
"vision_model.transformer.layers.1.self_attn.o_proj",
"vision_model.transformer.layers.1.mlp.fc1",
"vision_model.transformer.layers.1.mlp.fc2",
"vision_model.transformer.layers.2.self_attn.q_proj",
"vision_model.transformer.layers.2.self_attn.k_proj",
"vision_model.transformer.layers.2.self_attn.v_proj",
"vision_model.transformer.layers.2.self_attn.o_proj",
"vision_model.transformer.layers.2.mlp.fc1",
"vision_model.transformer.layers.2.mlp.fc2",
"vision_model.transformer.layers.3.self_attn.q_proj",
"vision_model.transformer.layers.3.self_attn.k_proj",
"vision_model.transformer.layers.3.self_attn.v_proj",
"vision_model.transformer.layers.3.self_attn.o_proj",
"vision_model.transformer.layers.3.mlp.fc1",
"vision_model.transformer.layers.3.mlp.fc2",
"vision_model.transformer.layers.4.self_attn.q_proj",
"vision_model.transformer.layers.4.self_attn.k_proj",
"vision_model.transformer.layers.4.self_attn.v_proj",
"vision_model.transformer.layers.4.self_attn.o_proj",
"vision_model.transformer.layers.4.mlp.fc1",
"vision_model.transformer.layers.4.mlp.fc2",
"vision_model.transformer.layers.5.self_attn.q_proj",
"vision_model.transformer.layers.5.self_attn.k_proj",
"vision_model.transformer.layers.5.self_attn.v_proj",
"vision_model.transformer.layers.5.self_attn.o_proj",
"vision_model.transformer.layers.5.mlp.fc1",
"vision_model.transformer.layers.5.mlp.fc2",
"vision_model.transformer.layers.6.self_attn.q_proj",
"vision_model.transformer.layers.6.self_attn.k_proj",
"vision_model.transformer.layers.6.self_attn.v_proj",
"vision_model.transformer.layers.6.self_attn.o_proj",
"vision_model.transformer.layers.6.mlp.fc1",
"vision_model.transformer.layers.6.mlp.fc2",
"vision_model.transformer.layers.7.self_attn.q_proj",
"vision_model.transformer.layers.7.self_attn.k_proj",
"vision_model.transformer.layers.7.self_attn.v_proj",
"vision_model.transformer.layers.7.self_attn.o_proj",
"vision_model.transformer.layers.7.mlp.fc1",
"vision_model.transformer.layers.7.mlp.fc2",
"vision_model.transformer.layers.8.self_attn.q_proj",
"vision_model.transformer.layers.8.self_attn.k_proj",
"vision_model.transformer.layers.8.self_attn.v_proj",
"vision_model.transformer.layers.8.self_attn.o_proj",
"vision_model.transformer.layers.8.mlp.fc1",
"vision_model.transformer.layers.8.mlp.fc2",
"vision_model.transformer.layers.9.self_attn.q_proj",
"vision_model.transformer.layers.9.self_attn.k_proj",
"vision_model.transformer.layers.9.self_attn.v_proj",
"vision_model.transformer.layers.9.self_attn.o_proj",
"vision_model.transformer.layers.9.mlp.fc1",
"vision_model.transformer.layers.9.mlp.fc2",
"vision_model.transformer.layers.10.self_attn.q_proj",
"vision_model.transformer.layers.10.self_attn.k_proj",
"vision_model.transformer.layers.10.self_attn.v_proj",
"vision_model.transformer.layers.10.self_attn.o_proj",
"vision_model.transformer.layers.10.mlp.fc1",
"vision_model.transformer.layers.10.mlp.fc2",
"vision_model.transformer.layers.11.self_attn.q_proj",
"vision_model.transformer.layers.11.self_attn.k_proj",
"vision_model.transformer.layers.11.self_attn.v_proj",
"vision_model.transformer.layers.11.self_attn.o_proj",
"vision_model.transformer.layers.11.mlp.fc1",
"vision_model.transformer.layers.11.mlp.fc2",
"vision_model.transformer.layers.12.self_attn.q_proj",
"vision_model.transformer.layers.12.self_attn.k_proj",
"vision_model.transformer.layers.12.self_attn.v_proj",
"vision_model.transformer.layers.12.self_attn.o_proj",
"vision_model.transformer.layers.12.mlp.fc1",
"vision_model.transformer.layers.12.mlp.fc2",
"vision_model.transformer.layers.13.self_attn.q_proj",
"vision_model.transformer.layers.13.self_attn.k_proj",
"vision_model.transformer.layers.13.self_attn.v_proj",
"vision_model.transformer.layers.13.self_attn.o_proj",
"vision_model.transformer.layers.13.mlp.fc1",
"vision_model.transformer.layers.13.mlp.fc2",
"vision_model.transformer.layers.14.self_attn.q_proj",
"vision_model.transformer.layers.14.self_attn.k_proj",
"vision_model.transformer.layers.14.self_attn.v_proj",
"vision_model.transformer.layers.14.self_attn.o_proj",
"vision_model.transformer.layers.14.mlp.fc1",
"vision_model.transformer.layers.14.mlp.fc2",
"vision_model.transformer.layers.15.self_attn.q_proj",
"vision_model.transformer.layers.15.self_attn.k_proj",
"vision_model.transformer.layers.15.self_attn.v_proj",
"vision_model.transformer.layers.15.self_attn.o_proj",
"vision_model.transformer.layers.15.mlp.fc1",
"vision_model.transformer.layers.15.mlp.fc2",
"vision_model.transformer.layers.16.self_attn.q_proj",
"vision_model.transformer.layers.16.self_attn.k_proj",
"vision_model.transformer.layers.16.self_attn.v_proj",
"vision_model.transformer.layers.16.self_attn.o_proj",
"vision_model.transformer.layers.16.mlp.fc1",
"vision_model.transformer.layers.16.mlp.fc2",
"vision_model.transformer.layers.17.self_attn.q_proj",
"vision_model.transformer.layers.17.self_attn.k_proj",
"vision_model.transformer.layers.17.self_attn.v_proj",
"vision_model.transformer.layers.17.self_attn.o_proj",
"vision_model.transformer.layers.17.mlp.fc1",
"vision_model.transformer.layers.17.mlp.fc2",
"vision_model.transformer.layers.18.self_attn.q_proj",
"vision_model.transformer.layers.18.self_attn.k_proj",
"vision_model.transformer.layers.18.self_attn.v_proj",
"vision_model.transformer.layers.18.self_attn.o_proj",
"vision_model.transformer.layers.18.mlp.fc1",
"vision_model.transformer.layers.18.mlp.fc2",
"vision_model.transformer.layers.19.self_attn.q_proj",
"vision_model.transformer.layers.19.self_attn.k_proj",
"vision_model.transformer.layers.19.self_attn.v_proj",
"vision_model.transformer.layers.19.self_attn.o_proj",
"vision_model.transformer.layers.19.mlp.fc1",
"vision_model.transformer.layers.19.mlp.fc2",
"vision_model.transformer.layers.20.self_attn.q_proj",
"vision_model.transformer.layers.20.self_attn.k_proj",
"vision_model.transformer.layers.20.self_attn.v_proj",
"vision_model.transformer.layers.20.self_attn.o_proj",
"vision_model.transformer.layers.20.mlp.fc1",
"vision_model.transformer.layers.20.mlp.fc2",
"vision_model.transformer.layers.21.self_attn.q_proj",
"vision_model.transformer.layers.21.self_attn.k_proj",
"vision_model.transformer.layers.21.self_attn.v_proj",
"vision_model.transformer.layers.21.self_attn.o_proj",
"vision_model.transformer.layers.21.mlp.fc1",
"vision_model.transformer.layers.21.mlp.fc2",
"vision_model.transformer.layers.22.self_attn.q_proj",
"vision_model.transformer.layers.22.self_attn.k_proj",
"vision_model.transformer.layers.22.self_attn.v_proj",
"vision_model.transformer.layers.22.self_attn.o_proj",
"vision_model.transformer.layers.22.mlp.fc1",
"vision_model.transformer.layers.22.mlp.fc2",
"vision_model.transformer.layers.23.self_attn.q_proj",
"vision_model.transformer.layers.23.self_attn.k_proj",
"vision_model.transformer.layers.23.self_attn.v_proj",
"vision_model.transformer.layers.23.self_attn.o_proj",
"vision_model.transformer.layers.23.mlp.fc1",
"vision_model.transformer.layers.23.mlp.fc2",
"vision_model.transformer.layers.24.self_attn.q_proj",
"vision_model.transformer.layers.24.self_attn.k_proj",
"vision_model.transformer.layers.24.self_attn.v_proj",
"vision_model.transformer.layers.24.self_attn.o_proj",
"vision_model.transformer.layers.24.mlp.fc1",
"vision_model.transformer.layers.24.mlp.fc2",
"vision_model.transformer.layers.25.self_attn.q_proj",
"vision_model.transformer.layers.25.self_attn.k_proj",
"vision_model.transformer.layers.25.self_attn.v_proj",
"vision_model.transformer.layers.25.self_attn.o_proj",
"vision_model.transformer.layers.25.mlp.fc1",
"vision_model.transformer.layers.25.mlp.fc2",
"vision_model.transformer.layers.26.self_attn.q_proj",
"vision_model.transformer.layers.26.self_attn.k_proj",
"vision_model.transformer.layers.26.self_attn.v_proj",
"vision_model.transformer.layers.26.self_attn.o_proj",
"vision_model.transformer.layers.26.mlp.fc1",
"vision_model.transformer.layers.26.mlp.fc2",
"vision_model.transformer.layers.27.self_attn.q_proj",
"vision_model.transformer.layers.27.self_attn.k_proj",
"vision_model.transformer.layers.27.self_attn.v_proj",
"vision_model.transformer.layers.27.self_attn.o_proj",
"vision_model.transformer.layers.27.mlp.fc1",
"vision_model.transformer.layers.27.mlp.fc2",
"vision_model.transformer.layers.28.self_attn.q_proj",
"vision_model.transformer.layers.28.self_attn.k_proj",
"vision_model.transformer.layers.28.self_attn.v_proj",
"vision_model.transformer.layers.28.self_attn.o_proj",
"vision_model.transformer.layers.28.mlp.fc1",
"vision_model.transformer.layers.28.mlp.fc2",
"vision_model.transformer.layers.29.self_attn.q_proj",
"vision_model.transformer.layers.29.self_attn.k_proj",
"vision_model.transformer.layers.29.self_attn.v_proj",
"vision_model.transformer.layers.29.self_attn.o_proj",
"vision_model.transformer.layers.29.mlp.fc1",
"vision_model.transformer.layers.29.mlp.fc2",
"vision_model.transformer.layers.30.self_attn.q_proj",
"vision_model.transformer.layers.30.self_attn.k_proj",
"vision_model.transformer.layers.30.self_attn.v_proj",
"vision_model.transformer.layers.30.self_attn.o_proj",
"vision_model.transformer.layers.30.mlp.fc1",
"vision_model.transformer.layers.30.mlp.fc2",
"vision_model.transformer.layers.31.self_attn.q_proj",
"vision_model.transformer.layers.31.self_attn.k_proj",
"vision_model.transformer.layers.31.self_attn.v_proj",
"vision_model.transformer.layers.31.self_attn.o_proj",
"vision_model.transformer.layers.31.mlp.fc1",
"vision_model.transformer.layers.31.mlp.fc2",
"vision_model.global_transformer.layers.0.self_attn.q_proj",
"vision_model.global_transformer.layers.0.self_attn.k_proj",
"vision_model.global_transformer.layers.0.self_attn.v_proj",
"vision_model.global_transformer.layers.0.self_attn.o_proj",
"vision_model.global_transformer.layers.0.mlp.fc1",
"vision_model.global_transformer.layers.0.mlp.fc2",
"vision_model.global_transformer.layers.1.self_attn.q_proj",
"vision_model.global_transformer.layers.1.self_attn.k_proj",
"vision_model.global_transformer.layers.1.self_attn.v_proj",
"vision_model.global_transformer.layers.1.self_attn.o_proj",
"vision_model.global_transformer.layers.1.mlp.fc1",
"vision_model.global_transformer.layers.1.mlp.fc2",
"vision_model.global_transformer.layers.2.self_attn.q_proj",
"vision_model.global_transformer.layers.2.self_attn.k_proj",
"vision_model.global_transformer.layers.2.self_attn.v_proj",
"vision_model.global_transformer.layers.2.self_attn.o_proj",
"vision_model.global_transformer.layers.2.mlp.fc1",
"vision_model.global_transformer.layers.2.mlp.fc2",
"vision_model.global_transformer.layers.3.self_attn.q_proj",
"vision_model.global_transformer.layers.3.self_attn.k_proj",
"vision_model.global_transformer.layers.3.self_attn.v_proj",
"vision_model.global_transformer.layers.3.self_attn.o_proj",
"vision_model.global_transformer.layers.3.mlp.fc1",
"vision_model.global_transformer.layers.3.mlp.fc2",
"vision_model.global_transformer.layers.4.self_attn.q_proj",
"vision_model.global_transformer.layers.4.self_attn.k_proj",
"vision_model.global_transformer.layers.4.self_attn.v_proj",
"vision_model.global_transformer.layers.4.self_attn.o_proj",
"vision_model.global_transformer.layers.4.mlp.fc1",
"vision_model.global_transformer.layers.4.mlp.fc2",
"vision_model.global_transformer.layers.5.self_attn.q_proj",
"vision_model.global_transformer.layers.5.self_attn.k_proj",
"vision_model.global_transformer.layers.5.self_attn.v_proj",
"vision_model.global_transformer.layers.5.self_attn.o_proj",
"vision_model.global_transformer.layers.5.mlp.fc1",
"vision_model.global_transformer.layers.5.mlp.fc2",
"vision_model.global_transformer.layers.6.self_attn.q_proj",
"vision_model.global_transformer.layers.6.self_attn.k_proj",
"vision_model.global_transformer.layers.6.self_attn.v_proj",
"vision_model.global_transformer.layers.6.self_attn.o_proj",
"vision_model.global_transformer.layers.6.mlp.fc1",
"vision_model.global_transformer.layers.6.mlp.fc2",
"vision_model.global_transformer.layers.7.self_attn.q_proj",
"vision_model.global_transformer.layers.7.self_attn.k_proj",
"vision_model.global_transformer.layers.7.self_attn.v_proj",
"vision_model.global_transformer.layers.7.self_attn.o_proj",
"vision_model.global_transformer.layers.7.mlp.fc1",
"vision_model.global_transformer.layers.7.mlp.fc2",
"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.cross_attn.q_proj",
"language_model.model.layers.3.cross_attn.k_proj",
"language_model.model.layers.3.cross_attn.v_proj",
"language_model.model.layers.3.cross_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.cross_attn.q_proj",
"language_model.model.layers.8.cross_attn.k_proj",
"language_model.model.layers.8.cross_attn.v_proj",
"language_model.model.layers.8.cross_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.cross_attn.q_proj",
"language_model.model.layers.13.cross_attn.k_proj",
"language_model.model.layers.13.cross_attn.v_proj",
"language_model.model.layers.13.cross_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.cross_attn.q_proj",
"language_model.model.layers.18.cross_attn.k_proj",
"language_model.model.layers.18.cross_attn.v_proj",
"language_model.model.layers.18.cross_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.cross_attn.q_proj",
"language_model.model.layers.23.cross_attn.k_proj",
"language_model.model.layers.23.cross_attn.v_proj",
"language_model.model.layers.23.cross_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.cross_attn.q_proj",
"language_model.model.layers.28.cross_attn.k_proj",
"language_model.model.layers.28.cross_attn.v_proj",
"language_model.model.layers.28.cross_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.cross_attn.q_proj",
"language_model.model.layers.33.cross_attn.k_proj",
"language_model.model.layers.33.cross_attn.v_proj",
"language_model.model.layers.33.cross_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.cross_attn.q_proj",
"language_model.model.layers.38.cross_attn.k_proj",
"language_model.model.layers.38.cross_attn.v_proj",
"language_model.model.layers.38.cross_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.lm_head",
"multi_modal_projector"
],
"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": {
"eos_token_id": [
128001,
128008,
128009
],
"model_type": "mllama_text_model",
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"torch_dtype": "bfloat16"
},
"torch_dtype": "float16",
"transformers_version": "4.47.1",
"vision_config": {
"image_size": 560,
"model_type": "mllama_vision_model",
"torch_dtype": "bfloat16"
}
}