{ "ablation_use_image": true, "ablation_use_ocr": true, "ablation_use_ocr_aug": true, "ablation_use_qaclip": false, "architectures": [ "OpenViVQAModel" ], "char_max_num": 50, "char_num": 168, "clip_late_adapter": false, "clip_vision_name": "openai/clip-vit-base-patch16", "decoder_start_token_id": 0, "do_center_crop": false, "do_resize": true, "eos_token_id": 1, "generation_max_new_tokens": 56, "generation_num_beams": 4, "image_mean": [ 0.48145466, 0.4578275, 0.40821073 ], "image_size": null, "image_std": [ 0.26862954, 0.26130258, 0.27577711 ], "model_type": "openvivqa", "ocr_aug_mode": "separate", "ocr_cuda_device": "cuda:0", "ocr_d_det": 256, "ocr_d_rec": 256, "ocr_edit_distance": 2, "ocr_feature_norm": "layernorm", "ocr_jaccard_dupe": 0.78, "ocr_lowercase": true, "ocr_max_2d_position_embeddings": 1024, "ocr_max_non_alnum_ratio": 0.6, "ocr_max_scene_text": 180, "ocr_min_text_len_keep": 2, "ocr_num_distances": 32, "ocr_related": "augment", "ocrseq_dropout": 0.1, "ocrseq_margin_frac": 0.14, "ocrseq_pool_size": 3, "ocrseq_use_spatial": true, "pad_token_id": 0, "qa_clip_d_text": null, "text_max_input_length": 32, "text_max_target_length": 56, "torch_dtype": "float32", "transformers_version": "4.45.2", "twc_adv_probability": 0.6, "twc_answer_weight": 0.1, "twc_feature": "fused", "twc_label_list": [ 0.9, 0.9 ], "twc_loss": "bce", "twc_mask_same_text": false, "twc_objective": "lexical", "twc_queue_size": 0, "twc_queue_start": 1000, "twc_related_train": "correct", "twc_temperature_init": 0.07, "twc_view": "shared", "twc_weight": 1.0, "use_twc": true, "vit5_name": "VietAI/vit5-base" }