| { |
| "bits": 4, |
| "data_type": "int", |
| "group_size": 128, |
| "sym": true, |
| "batch_size": 1, |
| "iters": 500, |
| "low_gpu_mem_usage": true, |
| "nsamples": 32, |
| "seqlen": 256, |
| "to_quant_block_names": "model.language_model.layers", |
| "autoround_version": "0.12.2", |
| "provider": "auto-round", |
| "quant_method": "awq", |
| "zero_point": false, |
| "version": "gemm", |
| "modules_to_not_convert": [ |
| "model.vision_tower.patch_embedder.input_proj", |
| "model.language_model.layers.14.self_attn.k_proj", |
| "model.language_model.layers.9.self_attn.q_proj", |
| "model.vision_tower", |
| "model.language_model.per_layer_model_projection", |
| "model.language_model.layers.9.self_attn.v_proj", |
| "model.language_model.layers.24.self_attn.q_proj", |
| "model.language_model.layers.24.self_attn.o_proj", |
| "model.language_model.layers.9.self_attn.o_proj", |
| "model.language_model.layers.17.self_attn.q_proj", |
| "model.language_model.layers.14.self_attn.q_proj", |
| "model.audio_tower.output_proj", |
| "model.language_model.layers.14.self_attn.v_proj", |
| "model.language_model.layers.18.self_attn.q_proj", |
| "model.language_model.layers.20.self_attn.q_proj", |
| "model.language_model.layers.33.self_attn.q_proj", |
| "model.embed_audio.embedding_projection", |
| "model.language_model.layers.33.self_attn.o_proj", |
| "model.language_model.layers.25.self_attn.o_proj", |
| "model.language_model.layers.20.self_attn.o_proj", |
| "model.language_model.layers.21.self_attn.q_proj", |
| "lm_head", |
| "model.language_model.layers.30.self_attn.o_proj", |
| "model.language_model.layers.19.self_attn.o_proj", |
| "model.language_model.layers.26.self_attn.q_proj", |
| "model.language_model.layers.31.self_attn.q_proj", |
| "model.language_model.layers.16.self_attn.o_proj", |
| "model.language_model.layers.4.self_attn.v_proj", |
| "model.audio_tower.subsample_conv_projection.input_proj_linear", |
| "model.language_model.layers.18.self_attn.o_proj", |
| "model.language_model.layers.22.self_attn.o_proj", |
| "model.language_model.layers.29.self_attn.o_proj", |
| "model.language_model.layers.34.self_attn.q_proj", |
| "model.audio_tower", |
| "model.language_model.layers.23.self_attn.o_proj", |
| "model.audio_tower.layers", |
| "model.language_model.layers.27.self_attn.q_proj", |
| "model.language_model.layers.25.self_attn.q_proj", |
| "model.language_model.layers.31.self_attn.o_proj", |
| "model.language_model.layers.4.self_attn.q_proj", |
| "model.language_model.layers.23.self_attn.q_proj", |
| "model.language_model.layers.22.self_attn.q_proj", |
| "model.language_model.layers.17.self_attn.o_proj", |
| "model.language_model.layers.4.self_attn.k_proj", |
| "model.language_model.layers.21.self_attn.o_proj", |
| "model.language_model.layers.28.self_attn.o_proj", |
| "model.language_model.layers.30.self_attn.q_proj", |
| "model.language_model.layers.27.self_attn.o_proj", |
| "model.embed_vision.embedding_projection", |
| "model.vision_tower.encoder.layers", |
| "model.language_model.layers.26.self_attn.o_proj", |
| "model.embed_audio", |
| "model.language_model.layers.15.self_attn.o_proj", |
| "model.language_model.layers.9.self_attn.k_proj", |
| "model.language_model.layers.15.self_attn.q_proj", |
| "model.language_model.layers.34.self_attn.o_proj", |
| "model.language_model.layers.29.self_attn.q_proj", |
| "model.language_model.layers.32.self_attn.o_proj", |
| "model.embed_vision", |
| "model.language_model.layers.28.self_attn.q_proj", |
| "model.language_model.layers.4.self_attn.o_proj", |
| "model.language_model.layers.14.self_attn.o_proj", |
| "model.language_model.layers.19.self_attn.q_proj", |
| "model.language_model.layers.32.self_attn.q_proj", |
| "model.language_model.layers.16.self_attn.q_proj" |
| ] |
| } |
