| { | |
| "architectures": [ | |
| "LlavaForConditionalGeneration" | |
| ], | |
| "ignore_index": -100, | |
| "image_seq_length": 576, | |
| "image_token_index": 32000, | |
| "model_type": "llava", | |
| "projector_hidden_act": "gelu", | |
| "text_config": { | |
| "head_dim": 2, | |
| "hidden_size": 8, | |
| "intermediate_size": 32, | |
| "model_type": "llama", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 2, | |
| "vocab_size": 32005 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.0.dev0", | |
| "vision_config": { | |
| "hidden_size": 8, | |
| "image_size": 336, | |
| "intermediate_size": 32, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "patch_size": 14, | |
| "projection_dim": 8 | |
| }, | |
| "vision_feature_layer": -2, | |
| "vision_feature_select_strategy": "default" | |
| } | |