| { | |
| "_name_or_path": "/home/mgoin/.cache/huggingface/hub/models--microsoft--Phi-3.5-vision-instruct/snapshots/4a0d683eba9f1d0cbfb6151705d1ee73c25a80ca", | |
| "architectures": [ | |
| "Phi3VForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_phi3_v.Phi3VConfig", | |
| "AutoModelForCausalLM": "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": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": true, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "memoryless", | |
| "observer_kwargs": {}, | |
| "strategy": "token", | |
| "symmetric": true, | |
| "type": "int" | |
| }, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "minmax", | |
| "observer_kwargs": {}, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "int-quantized", | |
| "global_compression_ratio": 1.1045610202550211, | |
| "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": [ | |
| 1.0800000429153442, | |
| 1.1100000143051147, | |
| 1.1399999856948853, | |
| 1.340000033378601, | |
| 1.5899999141693115, | |
| 1.600000023841858, | |
| 1.6200000047683716, | |
| 2.620000123977661, | |
| 3.2300000190734863, | |
| 3.2300000190734863, | |
| 4.789999961853027, | |
| 7.400000095367432, | |
| 7.700000286102295, | |
| 9.09000015258789, | |
| 12.199999809265137, | |
| 17.670000076293945, | |
| 24.46000099182129, | |
| 28.57000160217285, | |
| 30.420001983642578, | |
| 30.840002059936523, | |
| 32.590003967285156, | |
| 32.93000411987305, | |
| 42.320003509521484, | |
| 44.96000289916992, | |
| 50.340003967285156, | |
| 50.45000457763672, | |
| 57.55000305175781, | |
| 57.93000411987305, | |
| 58.21000289916992, | |
| 60.1400032043457, | |
| 62.61000442504883, | |
| 62.62000274658203, | |
| 62.71000289916992, | |
| 63.1400032043457, | |
| 63.1400032043457, | |
| 63.77000427246094, | |
| 63.93000411987305, | |
| 63.96000289916992, | |
| 63.970001220703125, | |
| 64.02999877929688, | |
| 64.06999969482422, | |
| 64.08000183105469, | |
| 64.12000274658203, | |
| 64.41000366210938, | |
| 64.4800033569336, | |
| 64.51000213623047, | |
| 64.52999877929688, | |
| 64.83999633789062 | |
| ], | |
| "short_factor": [ | |
| 1.08, | |
| 1.1, | |
| 1.1300000000000001, | |
| 1.2800000000000002, | |
| 1.3100000000000003, | |
| 1.4500000000000004, | |
| 1.4500000000000004, | |
| 1.9500000000000008, | |
| 2.030000000000001, | |
| 2.4299999999999926, | |
| 2.5699999999999896, | |
| 2.9499999999999815, | |
| 3.729999999999965, | |
| 3.869999999999962, | |
| 4.189999999999955, | |
| 4.43999999999995, | |
| 4.6399999999999455, | |
| 4.979999999999938, | |
| 5.159999999999934, | |
| 5.279999999999932, | |
| 5.759999999999922, | |
| 5.889999999999919, | |
| 5.889999999999919, | |
| 5.969999999999917, | |
| 6.089999999999915, | |
| 6.2799999999999105, | |
| 6.7699999999999, | |
| 6.8899999999998975, | |
| 7.109999999999893, | |
| 7.129999999999892, | |
| 7.179999999999891, | |
| 7.289999999999889, | |
| 7.339999999999888, | |
| 7.559999999999883, | |
| 7.619999999999882, | |
| 7.69999999999988, | |
| 7.879999999999876, | |
| 7.879999999999876, | |
| 7.879999999999876, | |
| 7.939999999999875, | |
| 7.949999999999875, | |
| 7.979999999999874, | |
| 8.19999999999987, | |
| 8.439999999999864, | |
| 8.469999999999864, | |
| 8.589999999999861, | |
| 8.809999999999857, | |
| 8.999999999999853 | |
| ], | |
| "type": "su" | |
| }, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 262144, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32064 | |
| } |