{ "_commit_hash": null, "architectures": [ "InstructBlipForConditionalGeneration" ], "initializer_factor": 1.0, "initializer_range": 0.02, "is_encoder_decoder": true, "model_type": "instructblip", "num_query_tokens": 32, "qformer_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_probs_dropout_prob": 0.1, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "classifier_dropout": null, "cross_attention_frequency": 2, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_hidden_size": 1408, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-12, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 512, "min_length": 0, "model_type": "instructblip_qformer", "no_repeat_ngram_size": 0, "num_attention_heads": 12, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 12, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "position_embedding_type": "absolute", "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.30.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "vocab_size": 30523 }, "text_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "T5ForConditionalGeneration" ], "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "d_ff": 10240, "d_kv": 64, "d_model": 4096, "decoder_start_token_id": 0, "dense_act_fn": "gelu", "diversity_penalty": 0.0, "do_sample": false, "dropout_rate": 0.1, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 1, "exponential_decay_length_penalty": null, "feed_forward_proj": "gated-gelu", "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_factor": 1.0, "is_decoder": false, "is_encoder_decoder": true, "is_gated_act": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_epsilon": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "t5", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_decoder_layers": 24, "num_heads": 64, "num_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_past": true, "output_scores": false, "pad_token_id": 0, "prefix": null, "problem_type": null, "pruned_heads": {}, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "transformers_version": "4.30.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 32128 }, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": null, "use_decoder_only_language_model": false, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1408, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 224, "initializer_factor": 1.0, "initializer_range": 1e-10, "intermediate_size": 6144, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "instructblip_vision_model", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 39, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "projection_dim": 512, "pruned_heads": {}, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.30.0.dev0", "typical_p": 1.0, "use_bfloat16": false } }