| { |
| "architectures": [ |
| "Blip2ForConditionalGeneration" |
| ], |
| "image_text_hidden_size": 256, |
| "image_token_index": null, |
| "initializer_factor": 1.0, |
| "initializer_range": 0.02, |
| "is_encoder_decoder": true, |
| "model_type": "blip-2", |
| "num_query_tokens": 32, |
| "qformer_config": { |
| "_attn_implementation_autoset": true, |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "cross_attention_frequency": 2, |
| "encoder_hidden_size": 1408, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "blip_2_qformer", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "position_embedding_type": "absolute", |
| "torch_dtype": "float32", |
| "use_qformer_text_input": false, |
| "vocab_size": 30522 |
| }, |
| "text_config": { |
| "_name_or_path": "/media/gregor/DATA/projects/wuerzburg/mblip/checkpoints/mt0-xl/07_24_2023_08_03_33-1-79282", |
| "architectures": [ |
| "MT5ForConditionalGeneration" |
| ], |
| "classifier_dropout": 0.0, |
| "d_ff": 5120, |
| "d_kv": 64, |
| "d_model": 2048, |
| "dense_act_fn": "gelu_new", |
| "dropout_rate": 0.1, |
| "feed_forward_proj": "gated-gelu", |
| "initializer_factor": 1.0, |
| "is_gated_act": true, |
| "layer_norm_epsilon": 1e-06, |
| "model_type": "mt5", |
| "num_decoder_layers": 24, |
| "num_heads": 32, |
| "num_layers": 24, |
| "output_past": true, |
| "relative_attention_max_distance": 128, |
| "relative_attention_num_buckets": 32, |
| "torch_dtype": "float32", |
| "use_cache": true, |
| "vocab_size": 250112 |
| }, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.0.dev0", |
| "use_decoder_only_language_model": false, |
| "vision_config": { |
| "_attn_implementation_autoset": true, |
| "attention_dropout": 0.0, |
| "dropout": 0.0, |
| "hidden_act": "gelu", |
| "hidden_size": 1408, |
| "image_size": 224, |
| "initializer_factor": 1.0, |
| "initializer_range": 1e-10, |
| "intermediate_size": 6144, |
| "layer_norm_eps": 1e-06, |
| "model_type": "blip_2_vision_model", |
| "num_attention_heads": 16, |
| "num_channels": 3, |
| "num_hidden_layers": 39, |
| "patch_size": 14, |
| "projection_dim": 512, |
| "qkv_bias": true, |
| "torch_dtype": "float32" |
| } |
| } |
|
|
