| { | |
| "_commit_hash": null, | |
| "_name_or_path": "path", | |
| "architectures": [ | |
| "GroundedBLIPLMForConditionalGeneration" | |
| ], | |
| "detection_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "ape": false, | |
| "architectures": null, | |
| "attn_drop_rate": 0.0, | |
| "aux_loss": true, | |
| "backbone": "swin_T_224_1k", | |
| "backbone_freeze_keywords": null, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "dec_layers": 6, | |
| "dec_n_points": 4, | |
| "dec_pred_bbox_embed_share": true, | |
| "decoder_start_token_id": null, | |
| "depths": [ | |
| 2, | |
| 2, | |
| 6, | |
| 2 | |
| ], | |
| "dilation": false, | |
| "dim_feedforward": 2048, | |
| "diversity_penalty": 0.0, | |
| "dn_bbox_coef": 1.0, | |
| "dn_box_noise_scale": 1.0, | |
| "dn_label_coef": 1.0, | |
| "dn_label_noise_ratio": 0.5, | |
| "dn_labelbook_size": 2000, | |
| "dn_number": 0, | |
| "do_sample": false, | |
| "drop_path_rate": 0.2, | |
| "drop_rate": 0.0, | |
| "dropout": 0.0, | |
| "early_stopping": false, | |
| "embed_dim": 96, | |
| "embed_init_tgt": true, | |
| "enc_layers": 6, | |
| "enc_n_points": 4, | |
| "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, | |
| "frozen_stages": -1, | |
| "fusion_dropout": 0.0, | |
| "fusion_droppath": 0.1, | |
| "hidden_dim": 256, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "in_chans": 3, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "iter_update": true, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "learnable_tgt_init": true, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_text_len": 256, | |
| "min_length": 0, | |
| "mlp_ratio": 4.0, | |
| "model_type": "blip_2_detection_model", | |
| "nheads": 8, | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_feature_levels": 4, | |
| "num_heads": [ | |
| 3, | |
| 6, | |
| 12, | |
| 24 | |
| ], | |
| "num_layers": 4, | |
| "num_patterns": 0, | |
| "num_queries": 900, | |
| "num_return_sequences": 1, | |
| "num_unicoder_layers": 0, | |
| "out_indices": [ | |
| 1, | |
| 2, | |
| 3 | |
| ], | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_norm": true, | |
| "patch_size": 4, | |
| "pe_temperatureh": 20, | |
| "pe_temperaturew": 20, | |
| "position_embedding": "sine", | |
| "pre_norm": false, | |
| "prefix": null, | |
| "pretrain_img_size": 224, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "qk_scale": null, | |
| "qkv_bias": true, | |
| "query_dim": 4, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "return_interm_indices": [ | |
| 1, | |
| 2, | |
| 3 | |
| ], | |
| "return_intermediate_dec": true, | |
| "sep_token_id": null, | |
| "sub_sentence_present": true, | |
| "suppress_tokens": null, | |
| "swintransformer_use_checkpoint": false, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "text_dropout": 0.0, | |
| "text_encoder_type": "bert-base-uncased", | |
| "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, | |
| "transformer_activation": "relu", | |
| "transformers_version": "4.31.0", | |
| "two_stage_bbox_embed_share": false, | |
| "two_stage_class_embed_share": false, | |
| "two_stage_type": "standard", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_checkpoint": true, | |
| "use_fusion_layer": true, | |
| "use_text_cross_attention": true, | |
| "use_text_enhancer": true, | |
| "use_transformer_ckpt": true, | |
| "window_size": 7 | |
| }, | |
| "image_text_hidden_size": 256, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "model_type": "blip-2", | |
| "num_query_tokens": 96, | |
| "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, | |
| "detection_encoder_hidden_size": 260, | |
| "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": "blip_2_qformer", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 12, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_dino_query_tokens": 64, | |
| "num_hidden_layers": 12, | |
| "num_return_sequences": 1, | |
| "num_vit_query_tokens": 32, | |
| "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": {}, | |
| "query_length": 96, | |
| "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": "4.31.0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "vocab_size": 30523 | |
| }, | |
| "ram_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "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, | |
| "delete_tag_index": [], | |
| "depths": [ | |
| 2, | |
| 2, | |
| 18, | |
| 2 | |
| ], | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "embed_dim": 192, | |
| "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, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_res": 384, | |
| "image_size": 384, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "med_config": "./med_config.json", | |
| "min_length": 0, | |
| "model_type": "blip_2_ram_model", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_heads": [ | |
| 6, | |
| 12, | |
| 24, | |
| 48 | |
| ], | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "prompt": "a picture of ", | |
| "pruned_heads": {}, | |
| "q2l_config": "./q2l_config.json", | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "tag_list": "./ram_tag_list.txt", | |
| "tag_list_chinese": "./ram_tag_list_chinese.txt", | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "textual_label_embedding_path": "./textual_label_embedding.pth", | |
| "tf_legacy_loss": false, | |
| "threshold": 0.68, | |
| "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": "4.31.0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "vision_width": 1536, | |
| "vit": "swin_l", | |
| "vit_ckpt_layer": 0, | |
| "vit_grad_ckpt": false, | |
| "window_size": 12 | |
| }, | |
| "text_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "LLaMAForCausalLM" | |
| ], | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 0, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 1, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 2048, | |
| "max_sequence_length": 2048, | |
| "min_length": 0, | |
| "model_type": "llama", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 40, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 40, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 32000, | |
| "prefix": null, | |
| "pretraining_tp": 1, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "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": "float16", | |
| "torchscript": false, | |
| "transformers_version": "4.31.0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "vocab_size": 32001 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": null, | |
| "use_decoder_only_language_model": true, | |
| "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, | |
| "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_range": 1e-10, | |
| "intermediate_size": 6144, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-06, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "blip_2_vision_model", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "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, | |
| "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": "4.31.0", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| } | |
| } | |