{ "_commit_hash": null, "_name_or_path": "work_dirs/visionllmv2-7b-gen-edit-det/", "architectures": [ "VisionLLMv2Model" ], "gdino_config": { "_commit_hash": null, "_name_or_path": "checkpoints/grounding-dino-tiny", "activation_dropout": 0.0, "activation_function": "relu", "add_cross_attention": false, "architectures": [ "GroundingDinoForObjectDetection" ], "attention_dropout": 0.0, "auxiliary_loss": true, "backbone_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_probs_dropout_prob": 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, "depths": [ 2, 2, 6, 2 ], "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.1, "early_stopping": false, "embed_dim": 96, "encoder_no_repeat_ngram_size": 0, "encoder_stride": 32, "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": 0.0, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 224, "initializer_range": 0.02, "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, "mlp_ratio": 4.0, "model_type": "swin", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_heads": [ 3, 6, 12, 24 ], "num_layers": 4, "num_return_sequences": 1, "out_features": [ "stage1", "stage2", "stage3", "stage4" ], "out_indices": [ 1, 2, 3, 4 ], "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 4, "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, "stage_names": [ "stem", "stage1", "stage2", "stage3", "stage4" ], "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": "4.34.0", "typical_p": 1.0, "use_absolute_embeddings": false, "use_bfloat16": false, "window_size": 7 }, "bad_words_ids": null, "bbox_cost": 5.0, "bbox_loss_coefficient": 5.0, "begin_suppress_tokens": null, "bos_token_id": null, "box_cost": 5.0, "box_weight": 5.0, "chunk_size_feed_forward": 0, "class_cost": 2.0, "class_weight": 2.0, "cross_attention_hidden_size": null, "d_model": 256, "decoder_attention_heads": 8, "decoder_bbox_embed_share": true, "decoder_ffn_dim": 2048, "decoder_layers": 6, "decoder_n_points": 4, "decoder_start_token_id": null, "dice_cost": 5.0, "dice_weight": 5.0, "disable_custom_kernels": false, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.1, "early_stopping": false, "embedding_init_target": true, "encoder_attention_heads": 8, "encoder_ffn_dim": 2048, "encoder_layers": 6, "encoder_n_points": 4, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "focal_alpha": 0.25, "forced_bos_token_id": null, "forced_eos_token_id": null, "fusion_dropout": 0.0, "fusion_droppath": 0.1, "giou_cost": 2.0, "giou_loss_coefficient": 2.0, "giou_weight": 2.0, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "init_std": 0.02, "is_decoder": false, "is_encoder_decoder": true, "l_hidden_size": 4096, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "mask_cost": 5.0, "mask_dim": 256, "mask_weight": 5.0, "max_length": 20, "max_text_len": 256, "min_length": 0, "model_type": "grounding-dino", "no_repeat_ngram_size": 0, "norm": "GN", "num_beam_groups": 1, "num_beams": 1, "num_embs": 4, "num_feature_levels": 4, "num_queries": 900, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "position_embedding_type": "sine", "positional_embedding_temperature": 20, "prefix": null, "problem_type": null, "pruned_heads": {}, "query_dim": 4, "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, "text_backbone_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, "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_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "init_std": 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": "grounding-dino-text-prenet", "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": "4.34.0", "type_vocab_size": 2, "typical_p": 1.0, "use_bfloat16": false, "vocab_size": 30522 }, "text_enhancer_dropout": 0.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "transformers_version": "4.36.0.dev0", "two_stage": true, "two_stage_bbox_embed_share": false, "typical_p": 1.0, "use_bfloat16": false }, "ip2p_config": { "_name_or_path": "visionllmv2/model/instruct_pix2pix/ip2p.json", "add_cross_attention": false, "architectures": [ "InstructPix2PixWithLLMEmbConfig" ], "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "cfg_drop_rate": 0.05, "cfg_scale": 7.5, "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, "embed_tokens": { "emb": "[EMB]", "emb2": "[EMB2]", "emb3": "[EMB3]", "emb4": "[EMB4]", "emb5": "[EMB5]", "emb6": "[EMB6]", "emb7": "[EMB7]", "emb8": "[EMB8]" }, "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" }, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "llm_hidden_size": 4096, "max_length": 20, "min_length": 0, "model_type": "instructpix2pix_with_llm_emb", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_decoder_layers": 1, "num_embed_tokens": 64, "num_encoder_layers": 1, "num_queries": 77, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sd_hidden_size": 768, "sd_model_id": "checkpoints/instruct-pix2pix", "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": "4.34.0", "trigger_token": "[EDIT]", "trigger_token_id": 32025, "typical_p": 1.0, "use_bfloat16": false }, "llm_config": { "_name_or_path": "checkpoints/vicuna-7b-v1.5", "add_cross_attention": false, "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "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": 2, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 4096, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 11008, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 4096, "min_length": 0, "model_type": "llama", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 32, "num_key_value_heads": 32, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "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-05, "rope_scaling": null, "rope_theta": 10000.0, "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": "4.34.0", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 32026 }, "model_type": "visionllmv2", "num_embs": 4, "num_embs_gen": 64, "pretrained_vl_bridge": null, "sd_config": { "_name_or_path": "visionllmv2/model/stable_diffusion/sd.json", "add_cross_attention": false, "architectures": [ "StableDiffusionWithLLMEmbConfig" ], "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "cfg_drop_rate": 0.1, "cfg_scale": 7.5, "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, "embed_tokens": { "emb": "[EMB]", "emb2": "[EMB2]", "emb3": "[EMB3]", "emb4": "[EMB4]", "emb5": "[EMB5]", "emb6": "[EMB6]", "emb7": "[EMB7]", "emb8": "[EMB8]" }, "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" }, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "llm_hidden_size": 4096, "max_length": 20, "min_length": 0, "model_type": "stable_diffusion_with_llm_emb", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_decoder_layers": 1, "num_embed_tokens": 64, "num_encoder_layers": 1, "num_queries": 77, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sd_hidden_size": 768, "sd_model_id": "checkpoints/stable-diffusion-v1-5", "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": "4.34.0", "trigger_token": "[GEN]", "trigger_token_id": 32024, "typical_p": 1.0, "use_bfloat16": false }, "torch_dtype": "bfloat16", "transformers_version": null, "unipose_config": { "_commit_hash": null, "_name_or_path": "checkpoints/unipose", "add_channel_attention": false, "add_cross_attention": false, "add_pos_value": false, "architectures": [ "UniPose" ], "aux_loss": true, "backbone": "swin_T_224_1k", "backbone_freeze_keywords": null, "bad_words_ids": null, "batch_norm_type": "FrozenBatchNorm2d", "batch_size": 2, "bbox_loss_coef": 5.0, "begin_suppress_tokens": null, "binary_query_selection": false, "bos_token_id": null, "box_attn_type": "roi_align", "chunk_size_feed_forward": 0, "clip_max_norm": 0.1, "cls_loss_coef": 2.0, "cross_attention_hidden_size": null, "dabdetr_deformable_decoder": false, "dabdetr_deformable_encoder": false, "dabdetr_yolo_like_anchor_update": false, "data_aug_max_size": 1333, "data_aug_scale_overlap": null, "data_aug_scales": [ 480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800 ], "data_aug_scales2_crop": [ 384, 600 ], "data_aug_scales2_resize": [ 400, 500, 600 ], "ddetr_lr_param": false, "dec_layer_number": null, "dec_layers": 6, "dec_n_points": 4, "dec_pred_bbox_embed_share": true, "dec_pred_class_embed_share": true, "decoder_layer_noise": false, "decoder_module_seq": [ "sa", "ca", "ffn" ], "decoder_sa_type": "sa", "decoder_start_token_id": null, "dice_loss_coef": 1.0, "dilation": false, "dim_feedforward": 2048, "diversity_penalty": 0.0, "dln_hw_noise": 0.2, "dln_xy_noise": 0.2, "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": 100, "do_sample": false, "dropout": 0.0, "early_stopping": false, "ema_decay": 0.9997, "ema_epoch": 0, "embed_init_tgt": true, "enc_layers": 6, "enc_loss_coef": 1.0, "enc_n_points": 4, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "epochs": 1, "exponential_decay_length_penalty": null, "ffn_extra_layernorm": false, "finetuning_task": null, "fix_refpoints_hw": -1, "fix_size": false, "focal_alpha": 0.25, "forced_bos_token_id": null, "forced_eos_token_id": null, "frozen_weights": null, "fusion_dropout": 0.0, "fusion_droppath": 0.1, "giou_loss_coef": 2.0, "hidden_dim": 256, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "interm_loss_coef": 1.0, "is_decoder": false, "is_encoder_decoder": false, "keypoint_loss_coef": 10.0, "l_hidden_size": 4096, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "lr": 1e-05, "lr_backbone": 1e-06, "lr_backbone_names": [ "backbone.0" ], "lr_drop": 7, "lr_drop_list": [ 31, 45 ], "lr_linear_proj_mult": 0.1, "lr_linear_proj_names": [ "reference_points", "sampling_offsets" ], "mask_loss_coef": 1.0, "masks": false, "match_unstable_error": true, "matcher_type": "HungarianMatcher", "max_length": 20, "max_text_len": 256, "min_length": 0, "modelname": "UniPose", "multi_step_lr": false, "nheads": 8, "nms_iou_threshold": -1, "no_interm_box_loss": false, "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_body_points": 68, "num_box_decoder_layers": 2, "num_classes": 2, "num_embs": 4, "num_feature_levels": 4, "num_patterns": 0, "num_queries": 900, "num_return_sequences": 1, "num_select": 50, "oks_loss_coef": 4.0, "onecyclelr": false, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "param_dict_type": "default", "pdetr3_bbox_embed_diff_each_layer": false, "pdetr3_refHW": -1, "pe_temperatureH": 20, "pe_temperatureW": 20, "position_embedding": "sine", "pre_norm": false, "prefix": null, "problem_type": null, "pruned_heads": {}, "query_dim": 4, "random_refpoints_xy": false, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "return_interm_indices": [ 1, 2, 3 ], "save_checkpoint_interval": 1, "sep_token_id": null, "set_cost_bbox": 5.0, "set_cost_class": 2.0, "set_cost_giou": 2.0, "set_cost_keypoint": 10.0, "set_cost_oks": 4.0, "shuffle_type": null, "sub_sentence_present": true, "suppress_tokens": null, "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": "float32", "torchscript": false, "train_projection": true, "transformer_activation": "relu", "transformers_version": null, "two_stage_add_query_num": 0, "two_stage_bbox_embed_share": false, "two_stage_class_embed_share": false, "two_stage_default_hw": 0.05, "two_stage_keep_all_tokens": false, "two_stage_learn_wh": false, "two_stage_pat_embed": 0, "two_stage_type": "standard", "typical_p": 1.0, "unic_layers": 0, "use_bfloat16": false, "use_cdn": true, "use_checkpoint": true, "use_deformable_box_attn": false, "use_detached_boxes_dec_out": false, "use_dn": false, "use_ema": false, "use_fusion_layer": true, "use_label_enc": true, "use_text_cross_attention": true, "use_text_enhancer": true, "use_transformer_ckpt": true, "weight_decay": 0.0001 }, "use_gdino": true, "use_ip2p": true, "use_llm_lora": false, "use_pixelshuffle": false, "use_region_encoder": true, "use_sd": true, "use_unipose": true, "vis_encoder_config": { "_name_or_path": "checkpoints/clip-vit-large-patch14-336", "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": "quick_gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 336, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "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": "clip_vision_model", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "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": 768, "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": "4.34.0", "typical_p": 1.0, "use_bfloat16": false }, "vis_output_layer": -2, "vl_bridge_type": "mlp2x_gelu" }