| { | |
| "_name_or_path": "/home/ec2-user/model_weights/Yi-VL-34B", | |
| "architectures": [ | |
| "YiVLForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 7168, | |
| "ignore_index": -100, | |
| "image_aspect_ratio": "pad", | |
| "image_grid_pinpoints": null, | |
| "image_token_index": 64002, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 20480, | |
| "max_position_embeddings": 4096, | |
| "mm_hidden_size": 1280, | |
| "mm_projector_type": "mlp2x_gelu_Norm", | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -2, | |
| "mm_vision_tower": "./vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448", | |
| "model_type": "llava", | |
| "moe_layer": null, | |
| "moe_mode": "easy", | |
| "num_attention_heads": 56, | |
| "num_hidden_layers": 60, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "projector_hidden_act": "gelu", | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 5000000.0, | |
| "text_config": { | |
| "model_type": "llama" | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.36.1", | |
| "tune_mm_mlp_adapter": false, | |
| "tune_vision_tower": true, | |
| "use_cache": false, | |
| "use_mm_proj": true, | |
| "vision_config": { | |
| "hidden_size": 1024, | |
| "image_size": 336, | |
| "intermediate_size": 4096, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "projection_dim": 768, | |
| "vocab_size": 32000 | |
| }, | |
| "vision_feature_layer": -2, | |
| "vision_feature_select_strategy": "default", | |
| "vocab_size": 64000 | |
| } | |