| { | |
| "architectures": [ | |
| "Blip2ForQformerTraining" | |
| ], | |
| "image_text_hidden_size": 256, | |
| "image_token_index": null, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "model_type": "blip-2", | |
| "num_query_tokens": 32, | |
| "qformer_config": { | |
| "_attn_implementation_autoset": true, | |
| "model_type": "blip_2_qformer", | |
| "use_qformer_text_input": true, | |
| "vocab_size": 30523 | |
| }, | |
| "text_config": { | |
| "model_type": "opt" | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.47.0.dev0", | |
| "use_decoder_only_language_model": true, | |
| "vision_config": { | |
| "_attn_implementation_autoset": true, | |
| "model_type": "blip_2_vision_model" | |
| } | |
| } | |