{ "architectures": [ "NemotronParseForConditionalGeneration" ], "auto_map": { "AutoConfig": "hf_nemotron_parse_config.NemotronParseConfig", "AutoModel": "hf_nemotron_parse_modeling.NemotronParseForConditionalGeneration", "AutoImageProcessor": "hf_nemotron_parse_processor.NemotronParseImageProcessor", "AutoProcessor": "hf_nemotron_parse_processor.NemotronParseProcessor" }, "bos_token_id": 0, "decoder": { "_attn_implementation": "sdpa", "_name_or_path": "", "activation_dropout": 0.0, "activation_function": "gelu", "add_cross_attention": true, "add_final_layer_norm": true, "architectures": null, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 0, "chunk_size_feed_forward": 0, "classifier_dropout": 0.0, "cross_attention_hidden_size": null, "d_model": 1024, "decoder_attention_heads": 16, "decoder_ffn_dim": 4096, "decoder_layerdrop": 0.0, "decoder_layers": 10, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dropout": 0.1, "early_stopping": false, "encoder_attention_heads": 16, "encoder_ffn_dim": 4096, "encoder_layerdrop": 0.0, "encoder_layers": 12, "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": 2, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "init_std": 0.02, "is_decoder": true, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "nemotron_parse_text", "no_repeat_ngram_size": 0, "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": 1, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "scale_embedding": true, "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": "4.51.3", "typical_p": 1.0, "use_bfloat16": true, "use_cache": true, "vocab_size": 52352 }, "decoder_start_token_id": 2, "encoder": { "_attn_implementation": "eager", "_name_or_path": "nvidia/C-RADIOv2-H", "adaptor_configs": {}, "adaptor_names": null, "add_cross_attention": false, "architectures": [ "RADIOModel" ], "args": { "aa": null, "amp": true, "amp_dtype": "bfloat16", "amp_impl": "native", "aug_repeats": 0, "aug_splits": 0, "bn_eps": null, "bn_momentum": null, "cache_dir": null, "channels_last": false, "checkpoint_hist": 10, "chk_keep_forever": 100, "class_map": "", "clip_grad": null, "clip_mode": "norm", "cls_token_per_teacher": true, "coco_annotations_file": "/datasets/coco2017-adlsa/annotations/captions_val2017.json", "coco_image_dir": "/datasets/coco2017-adlsa/val2017", "color_jitter": 0.4, "cooldown_epochs": 0, "cpe_max_size": 2048, "crd_loss": false, "crd_loss_weight": 0.8, "crop_pct": null, "cutmix": 0.0, "cutmix_minmax": null, "dataset_download": false, "debug_full_knn": false, "decay_epochs": 90, "decay_milestones": [ 90, 180, 270 ], "decay_rate": 0.1, "depchain": true, "dist_bn": "reduce", "dist_norm_weight": 0.0, "distributed": true, "drop": 0.0, "drop_block": null, "drop_connect": null, "drop_path": null, "dtype": "bfloat16", "epoch_repeats": 0.0, "eval": false, "eval_metric": "knn_top1", "eval_teacher": false, "eval_teacher_only": false, "eval_throughput": false, "fast_norm": false, "fd_loss_fn": "MSE", "feature_normalization": "SHIP_NORM", "feature_summarizer": "cls_token", "feature_upscale_factor": null, "force_new_wandb_id": false, "force_spectral_reparam": true, "freeze_bn": false, "fsdp": false, "fuser": "", "gp": null, "grad_accum_steps": 1, "grad_checkpointing": false, "head_init_bias": null, "head_init_scale": null, "head_warmup": 5, "head_weight_decay": 0.001, "hflip": 0.5, "img_size": null, "in_chans": null, "initial_checkpoint": null, "input_size": null, "interpolation": "", "layer_decay": null, "local_rank": 0, "log_interval": 50, "log_mlflow": false, "log_wandb": true, "loss_auto_balance": false, "lr_base": 0.1, "lr_base_scale": "", "lr_base_size": 256, "lr_cycle_decay": 0.5, "lr_cycle_limit": 1, "lr_cycle_mul": 1.0, "lr_k_decay": 1.0, "lr_noise": null, "lr_noise_pct": 0.67, "lr_noise_std": 1.0, "mean": null, "mesa": false, "min_lr": 0, "mixup": 0.0, "mixup_mode": "batch", "mixup_off_epoch": 0, "mixup_prob": 1.0, "mixup_switch_prob": 0.5, "mlp_hidden_size": 1520, "mlp_num_inner": 3, "mlp_version": "v2", "model": "vit_huge_patch16_224", "model_kwargs": {}, "model_norm": false, "momentum": 0.9, "no_aug": false, "no_ddp_bb": true, "no_prefetcher": false, "no_resume_opt": false, "num_classes": null, "opt_betas": null, "opt_eps": null, "patience_epochs": 10, "pin_mem": false, "prefetcher": true, "pretrained": false, "rank": 0, "ratio": [ 0.75, 1.3333333333333333 ], "recount": 1, "recovery_interval": 0, "register_multiple": 8, "remode": "pixel", "reprob": 0.0, "reset_loss_state": false, "resplit": false, "save_images": false, "scale": [ 0.5, 1.0 ], "sched": "cosine", "seed": 42, "smoothing": 0.1, "spectral_heads": false, "spectral_reparam": false, "split_bn": false, "start_epoch": null, "std": null, "stream_teachers": true, "sync_bn": false, "synchronize_step": false, "teachers": [ { "fd_normalize": false, "feature_distillation": true, "input_size": 378, "model": "ViT-H-14-378-quickgelu", "name": "clip", "pretrained": "dfn5b", "type": "open_clip", "use_summary": true }, { "fd_normalize": false, "feature_distillation": true, "input_size": 378, "model": "ViT-SO400M-14-SigLIP-384", "name": "siglip", "pretrained": "webli", "type": "open_clip", "use_summary": true }, { "fd_normalize": false, "feature_distillation": true, "input_size": 378, "model": "dinov2_vitg14_reg", "name": "dino_v2", "type": "dino_v2", "use_summary": true }, { "fd_normalize": false, "feature_distillation": true, "input_size": 1024, "model": "vit-h", "name": "sam", "type": "sam", "use_summary": false } ], "torchcompile": null, "torchscript": false, "train_interpolation": "random", "train_split": "train", "tta": 0, "use_coco": false, "use_multi_epochs_loader": false, "val_ema_only": false, "val_split": "val", "vflip": 0.0, "vitdet_version": 1, "wandb_entity": "", "wandb_job_type": "", "wandb_name": "", "wandb_project": "", "warmup_lr": 1e-05, "warmup_prefix": false, "worker_seeding": "all", "workers": 8, "world_size": 256 }, "auto_map": { "AutoConfig": "nvidia/C-RADIOv2-H--hf_model.RADIOConfig", "AutoModel": "nvidia/C-RADIOv2-H--hf_model.RADIOModel" }, "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, "feature_normalizer_config": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "inter_feature_normalizer_config": null, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_resolution": 2048, "min_length": 0, "model_type": "", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 16, "preferred_resolution": [ 768, 768 ], "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": "bfloat16", "torchscript": false, "transformers_version": "4.51.3", "typical_p": 1.0, "use_bfloat16": true, "version": "radio_v2.5-h", "vitdet_window_size": null }, "eos_token_id": 2, "image_size": [ 2048, 1648 ], "is_encoder_decoder": true, "max_sequence_length": 9000, "model_type": "nemotron_parse", "pad_token_id": 1, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.51.3", "vocab_size": 52327 }