| { | |
| "_name_or_path": "microsoft/Phi-3-vision-128k-instruct", | |
| "architectures": [ | |
| "Phi3VForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "microsoft/Phi-3-vision-128k-instruct--configuration_phi3_v.Phi3VConfig", | |
| "AutoModelForCausalLM": "microsoft/Phi-3-vision-128k-instruct--modeling_phi3_v.Phi3VForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "embd_layer": { | |
| "embedding_cls": "image", | |
| "hd_transform_order": "sub_glb", | |
| "projection_cls": "mlp", | |
| "use_hd_transform": true, | |
| "with_learnable_separator": true | |
| }, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "img_processor": { | |
| "image_dim_out": 1024, | |
| "model_name": "openai/clip-vit-large-patch14-336", | |
| "name": "clip_vision_model", | |
| "num_img_tokens": 144 | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "model_type": "phi3_v", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "original_max_position_embeddings": 4096, | |
| "pad_token_id": 32000, | |
| "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": 1.2120994032993202, | |
| "ignore": [ | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1", | |
| "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2", | |
| "model.vision_embed_tokens.img_projection.0", | |
| "model.vision_embed_tokens.img_projection.2", | |
| "lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed" | |
| }, | |
| "resid_pdrop": 0.0, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "long_factor": [ | |
| 1.0299999713897705, | |
| 1.0499999523162842, | |
| 1.0499999523162842, | |
| 1.0799999237060547, | |
| 1.2299998998641968, | |
| 1.2299998998641968, | |
| 1.2999999523162842, | |
| 1.4499999284744263, | |
| 1.5999999046325684, | |
| 1.6499998569488525, | |
| 1.8999998569488525, | |
| 2.859999895095825, | |
| 3.68999981880188, | |
| 5.419999599456787, | |
| 5.489999771118164, | |
| 5.489999771118164, | |
| 9.09000015258789, | |
| 11.579999923706055, | |
| 15.65999984741211, | |
| 15.769999504089355, | |
| 15.789999961853027, | |
| 18.360000610351562, | |
| 21.989999771118164, | |
| 23.079999923706055, | |
| 30.009998321533203, | |
| 32.35000228881836, | |
| 32.590003967285156, | |
| 35.56000518798828, | |
| 39.95000457763672, | |
| 53.840003967285156, | |
| 56.20000457763672, | |
| 57.95000457763672, | |
| 59.29000473022461, | |
| 59.77000427246094, | |
| 59.920005798339844, | |
| 61.190006256103516, | |
| 61.96000671386719, | |
| 62.50000762939453, | |
| 63.3700065612793, | |
| 63.48000717163086, | |
| 63.48000717163086, | |
| 63.66000747680664, | |
| 63.850006103515625, | |
| 64.08000946044922, | |
| 64.760009765625, | |
| 64.80001068115234, | |
| 64.81001281738281, | |
| 64.81001281738281 | |
| ], | |
| "short_factor": [ | |
| 1.05, | |
| 1.05, | |
| 1.05, | |
| 1.1, | |
| 1.1, | |
| 1.1, | |
| 1.2500000000000002, | |
| 1.2500000000000002, | |
| 1.4000000000000004, | |
| 1.4500000000000004, | |
| 1.5500000000000005, | |
| 1.8500000000000008, | |
| 1.9000000000000008, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.000000000000001, | |
| 2.1000000000000005, | |
| 2.1000000000000005, | |
| 2.2, | |
| 2.3499999999999996, | |
| 2.3499999999999996, | |
| 2.3499999999999996, | |
| 2.3499999999999996, | |
| 2.3999999999999995, | |
| 2.3999999999999995, | |
| 2.6499999999999986, | |
| 2.6999999999999984, | |
| 2.8999999999999977, | |
| 2.9499999999999975, | |
| 3.049999999999997, | |
| 3.049999999999997, | |
| 3.049999999999997 | |
| ], | |
| "type": "su" | |
| }, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.0", | |
| "use_cache": true, | |
| "vocab_size": 32064 | |
| } |