align implementation on transformers + include navit style changes (these changes are backward compatible)
e06a98d
| { | |
| "_name_or_path": "HuggingFaceM4/tiny-random-siglip", | |
| "architectures": [ | |
| "SiglipModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "HuggingFaceM4/tiny-random-siglip--configuration_siglip.SiglipConfig", | |
| "AutoModel": "HuggingFaceM4/tiny-random-siglip--modeling_siglip.SiglipModel" | |
| }, | |
| "initializer_factor": 1.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "siglip", | |
| "projection_dim": 512, | |
| "text_config": { | |
| "hidden_size": 144, | |
| "intermediate_size": 538, | |
| "model_type": "siglip_text_model", | |
| "num_attention_heads": 2, | |
| "num_hidden_layers": 3, | |
| "projection_dim": 64, | |
| "vocab_size": 32000 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.37.0.dev0", | |
| "vision_config": { | |
| "hidden_size": 144, | |
| "image_size": 30, | |
| "intermediate_size": 538, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 2, | |
| "num_hidden_layers": 3, | |
| "patch_size": 2, | |
| "projection_dim": 64 | |
| } | |
| } | |