| { | |
| "_name_or_path": "./hf/nllb-clip-large", | |
| "architectures": [ | |
| "NLLBCLIPModel" | |
| ], | |
| "initializer_factor": 1.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "clip", | |
| "projection_dim": 512, | |
| "text_config": { | |
| "encoder_ffn_dim": 8192, | |
| "encoder_layerdrop": 0, | |
| "encoder_layers": 24, | |
| "model_type": "clip_text_model", | |
| "num_hidden_layers": 24, | |
| "vocab_size": 256206 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.33.1", | |
| "vision_config": { | |
| "dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1280, | |
| "intermediate_size": 5120, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 32, | |
| "patch_size": 14, | |
| "projection_dim": 1024 | |
| } | |
| } | |