{ "_name_or_path": "Salesforce/instructblip-flan-t5-xl", "architectures": [ "InstructBlipForConditionalGeneration" ], "initializer_factor": 1.0, "initializer_range": 0.02, "is_encoder_decoder": true, "model_type": "instructblip", "num_query_tokens": 32, "qformer_config": { "classifier_dropout": null, "model_type": "instructblip_qformer", "vocab_size": 30523 }, "quantization_config": { "bnb_4bit_compute_dtype": "float32", "bnb_4bit_quant_type": "fp4", "bnb_4bit_use_double_quant": false, "llm_int8_enable_fp32_cpu_offload": true, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": null, "llm_int8_threshold": 6.0, "load_in_4bit": false, "load_in_8bit": true }, "text_config": { "architectures": [ "T5ForConditionalGeneration" ], "bos_token_id": 1, "classifier_dropout": 0.0, "d_ff": 5120, "d_kv": 64, "d_model": 2048, "decoder_start_token_id": 0, "dense_act_fn": "gelu", "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "gated-gelu", "initializer_factor": 1.0, "is_encoder_decoder": true, "is_gated_act": true, "layer_norm_epsilon": 1e-06, "model_type": "t5", "n_positions": 512, "num_decoder_layers": 24, "num_heads": 32, "num_layers": 24, "output_past": true, "pad_token_id": 0, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "task_specific_params": { "summarization": { "early_stopping": true, "length_penalty": 2.0, "max_length": 200, "min_length": 30, "no_repeat_ngram_size": 3, "num_beams": 4, "prefix": "summarize: " }, "translation_en_to_de": { "early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to German: " }, "translation_en_to_fr": { "early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to French: " }, "translation_en_to_ro": { "early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to Romanian: " } }, "tie_word_embeddings": false, "torch_dtype": "float32", "vocab_size": 32128 }, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.32.0.dev0", "use_decoder_only_language_model": false, "vision_config": { "dropout": 0.0, "initializer_factor": 1.0, "model_type": "instructblip_vision_model", "num_channels": 3 } }