| { | |
| "_attn_implementation": "flash_attention_2", | |
| "_commit_hash": null, | |
| "architectures": [ | |
| "Eagle3_VLForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_eagle3_vl.Eagle3_VLConfig", | |
| "AutoModel": "modeling_eagle3_vl.Eagle3_VLForConditionalGeneration", | |
| "AutoModelForCausalLM": "modeling_eagle3_vl.Eagle3_VLForConditionalGeneration" | |
| }, | |
| "downsample_ratio": 0.5, | |
| "dynamic_image_size": false, | |
| "image_token_index": 151669, | |
| "loss_version": "efficient_v2_cp_head", | |
| "max_dynamic_tiles": 12, | |
| "min_dynamic_tiles": 1, | |
| "mlp_checkpoint": false, | |
| "mlp_connector_layers": 2, | |
| "model_type": "eagle_3_vl", | |
| "pad2square": false, | |
| "select_layer": -1, | |
| "text_config": { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "Qwen/Qwen3-1.7B", | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151680 | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": null, | |
| "use_backbone_lora": 0, | |
| "use_llm_lora": 0, | |
| "use_pixel_shuffle": true, | |
| "use_thumbnail": false, | |
| "vision_config": { | |
| "_attn_implementation_autoset": true, | |
| "attention_dropout": 0.0, | |
| "full_attention_indexes": [ | |
| 7, | |
| 14, | |
| 21, | |
| 26 | |
| ], | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip2_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "num_patches": 256, | |
| "patch_size": 14, | |
| "torch_dtype": "bfloat16", | |
| "use_rope": false, | |
| "use_windows_attn": true, | |
| "window_size": 14 | |
| } | |
| } | |