| { | |
| "_name_or_path": "./TaiVision_base", | |
| "architectures": [ | |
| "TaiVisionForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_taivisionlm.TaiVisionLMConfig", | |
| "AutoModelForCausalLM": "modeling_taivisionlm.TaiVisionForCausalLM" | |
| }, | |
| "hidden_size": 2048, | |
| "ignore_index": -100, | |
| "image_token_index": 32000, | |
| "model_type": "taivisionlm", | |
| "num_image_tokens": 196, | |
| "projection_dim": 768, | |
| "text_config": { | |
| "architecture": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "hidden_size": 2048, | |
| "intermediate_size": 5632, | |
| "model_type": "llama", | |
| "num_hidden_layers": 22, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-05, | |
| "torch_dtype": "bfloat16", | |
| "vocab_size": 32001 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.0", | |
| "vision_config": { | |
| "model_type": "siglip_vision_model", | |
| "projection_dim": 768 | |
| } | |
| } | |