| { | |
| "_name_or_path": "LLM2CLIP-Openai-L-14", | |
| "architectures": [ | |
| "LLM2CLIPModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_clip.CLIPConfig", | |
| "AutoModel": "modeling_clip.LLM2CLIPModel" | |
| }, | |
| "initializer_factor": 1.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "clip", | |
| "projection_dim": 1280, | |
| "text_config": { | |
| "model_type": "clip_text_model" | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.2", | |
| "vision_config": { | |
| "dropout": 0.0, | |
| "hidden_size": 1024, | |
| "intermediate_size": 4096, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "projection_dim": 1280 | |
| } | |
| } | |