{ "_commit_hash": null, "_name_or_path": "/mnt/petrelfs/share_data/liuzhaoyang/share/vllm/internvl_scaleup_s3_3_ft_v1_ckpt_30000", "architectures": [ "VisionLLMv2Model" ], "downsample_ratio": 0.5, "gdino_config": { "_commit_hash": null, "_name_or_path": "checkpoints/grounding-dino-internimage-H", "`_dropout": 0.0, "activation_dropout": 0.0, "activation_function": "relu", "add_cross_attention": false, "architectures": [ "GroundingDinoForObjectDetection" ], "attention_dropout": 0.0, "auxiliary_loss": true, "backbone_config": { "model_type": "internimage-H" }, "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": 6144, "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": 6144, "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": "timbrooks/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": 92568, "typical_p": 1.0, "use_bfloat16": false }, "l_hidden_size": 6144, "llm_config": { "_name_or_path": "pretrained/internlm2-chat-20b/", "add_cross_attention": false, "architectures": [ "InternLM2ForCausalLM" ], "attention_bias": false, "attn_implementation": "flash_attention_2", "auto_map": { "AutoConfig": "configuration_internlm2.InternLM2Config", "AutoModel": "modeling_internlm2.InternLM2ForCausalLM", "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM" }, "bad_words_ids": null, "begin_suppress_tokens": null, "bias": false, "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": 6144, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 16384, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "min_length": 0, "model_type": "llama", "no_repeat_ngram_size": 0, "num_attention_heads": 48, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 48, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 2, "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": { "factor": 3.0, "type": "dynamic" }, "rope_theta": 1000000, "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": "bfloat16", "torchscript": false, "transformers_version": "4.34.0", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 92577 }, "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": 6144, "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": "runwayml/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": 92567, "typical_p": 1.0, "use_bfloat16": false }, "torch_dtype": "bfloat16", "transformers_version": null, "unipose_config": null, "use_gdino": true, "use_internvl": true, "use_ip2p": true, "use_llm_lora": false, "use_pixelshuffle": true, "use_region_encoder": false, "use_sd": true, "use_unipose": false, "v_hidden_size": 3200, "vis_encoder_config": { "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_intern_vit.InternVisionConfig", "AutoModel": "modeling_intern_vit.InternVisionModel" }, "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, "drop_path_rate": 0.4, "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": 3200, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 0.1, "initializer_range": 1e-10, "intermediate_size": 12800, "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": "clip_vision_model", "no_repeat_ngram_size": 0, "norm_type": "rms_norm", "num_attention_heads": 25, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 45, "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": {}, "qk_normalization": true, "qkv_bias": false, "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": "bfloat16", "torchscript": false, "transformers_version": "4.34.0", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": true }, "vis_output_layer": -1, "vl_bridge_type": "internvl" }