{ "_commit_hash": null, "_name_or_path": "./OpenGVLab/InternVL2-4B", "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "configuration_internvl_chat.InternVLChatConfig", "AutoModel": "modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_attn_implementation_autoset": false, "_name_or_path": "microsoft/Phi-3-mini-128k-instruct", "add_cross_attention": false, "architectures": [ "Phi3ForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_phi3.Phi3Config", "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" }, "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, "embd_pdrop": 0.0, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 32000, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 3072, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 8192, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 131072, "min_length": 0, "model_type": "phi3", "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, "original_max_position_embeddings": 4096, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 32000, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "resid_pdrop": 0.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": { "long_factor": [ 1.0299999713897705, 1.0499999523162842, 1.0499999523162842, 1.0799999237060547, 1.2299998998641968, 1.2299998998641968, 1.2999999523162842, 1.4499999284744263, 1.5999999046325684, 1.6499998569488525, 1.8999998569488525, 2.859999895095825, 3.68999981880188, 5.419999599456787, 5.489999771118164, 5.489999771118164, 9.09000015258789, 11.579999923706055, 15.65999984741211, 15.769999504089355, 15.789999961853027, 18.360000610351562, 21.989999771118164, 23.079999923706055, 30.009998321533203, 32.35000228881836, 32.590003967285156, 35.56000518798828, 39.95000457763672, 53.840003967285156, 56.20000457763672, 57.95000457763672, 59.29000473022461, 59.77000427246094, 59.920005798339844, 61.190006256103516, 61.96000671386719, 62.50000762939453, 63.3700065612793, 63.48000717163086, 63.48000717163086, 63.66000747680664, 63.850006103515625, 64.08000946044922, 64.760009765625, 64.80001068115234, 64.81001281738281, 64.81001281738281 ], "short_factor": [ 1.05, 1.05, 1.05, 1.1, 1.1, 1.1500000000000001, 1.2000000000000002, 1.2500000000000002, 1.3000000000000003, 1.3500000000000003, 1.5000000000000004, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.000000000000001, 2.0500000000000007, 2.0500000000000007, 2.0500000000000007, 2.1000000000000005, 2.1000000000000005, 2.1000000000000005, 2.1500000000000004, 2.1500000000000004, 2.3499999999999996, 2.549999999999999, 2.5999999999999988, 2.5999999999999988, 2.7499999999999982, 2.849999999999998, 2.849999999999998, 2.9499999999999975 ], "type": "su" }, "rope_theta": 10000.0, "sep_token_id": null, "sliding_window": 262144, "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": "4.47.1", "typical_p": 1.0, "use_bfloat16": true, "use_cache": true, "vocab_size": 32020 }, "max_dynamic_patch": 12, "min_dynamic_patch": 1, "model_type": "internvl_chat", "ps_version": "v2", "radio_config": { "_attn_implementation_autoset": true, "_name_or_path": "./nvidia/RADIO", "adaptor_names": null, "add_cross_attention": false, "architectures": [ "RADIOModel" ], "args": { "aa": null, "amp": false, "amp_dtype": "float16", "amp_impl": "native", "aug_repeats": 0, "aug_splits": 0, "auto_loss_balance_mode": "manual", "batch_size": 32, "bn_eps": null, "bn_momentum": null, "cache_dir": null, "channels_last": false, "checkpoint_hist": 10, "chk_keep_forever": 10, "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, "data_dir": [ [ "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/captioning/datacomp/dc1b/stage2", 0.95 ], [ "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/segmentation/sam/stage1", 0.05 ] ], "dataset": "nvgpt4", "dataset_download": false, "debug_full_knn": false, "decay_epochs": 90, "decay_milestones": [ 90, 180, 270 ], "decay_rate": 0.1, "device": "cuda:0", "dist_bn": "reduce", "distributed": true, "drop": 0.0, "drop_block": null, "drop_connect": null, "drop_path": null, "dtype": "bfloat16", "epoch_repeats": 0.0, "epochs": 50, "eval": false, "eval_metric": "knn_top1", "eval_teacher": false, "eval_teacher_only": false, "eval_throughput": false, "experiment": "checkpoints", "fast_norm": false, "feature_summarizer": "cls_token", "feature_upscale_factor": null, "force_new_wandb_id": false, "force_spectral_reparam": false, "fuser": "", "gp": null, "grad_accum_steps": 1, "grad_checkpointing": false, "head_init_bias": null, "head_init_scale": null, "hflip": 0.5, "img_size": null, "in_chans": null, "initial_checkpoint": "", "input_size": null, "interpolation": "", "layer_decay": null, "local_rank": 0, "log_interval": 50, "log_mlflow": false, "log_wandb": true, "loss": "cosine", "loss_auto_balance": false, "lr": 0.001, "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": { "gaussian_kl": false, "start_epoch": 100 }, "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_mlpnorm", "model_ema": { "decay": 0.9998, "force_cpu": false, "power": false, "power_stds": [ 0.05, 0.1 ], "start_epoch": 0 }, "model_kwargs": {}, "model_norm": true, "momentum": 0.9, "no_aug": false, "no_ddp_bb": false, "no_prefetcher": false, "no_resume_opt": false, "num_classes": null, "opt": "lamb", "opt_betas": null, "opt_eps": null, "opt_kwargs": { "filter_bias_and_bn": false }, "output": "/lustre/fs6/portfolios/llmservice/users/mranzinger/output/evfm/ohem/3-13-24_vit-h-16_bf16_ep50", "patience_epochs": 10, "pin_mem": false, "prefetcher": true, "pretrained": false, "rank": 0, "ratio": [ 0.75, 1.3333333333333333 ], "recount": 1, "recovery_interval": 0, "register_multiple": 16, "remode": "pixel", "reprob": 0.0, "resplit": false, "resume": "/lustre/fs6/portfolios/llmservice/users/mranzinger/output/evfm/ohem/3-13-24_vit-h-16_bf16_ep50/checkpoints/checkpoint-48.pth.tar", "save_images": false, "scale": [ 0.5, 1.0 ], "sched": "cosine", "sched_on_updates": true, "seed": 42, "smoothing": 0.1, "spectral_reparam": false, "split_bn": false, "start_epoch": null, "std": null, "steps_per_epoch": 2000, "sync_bn": false, "synchronize_step": true, "teachers": [ { "amp": true, "amp_dtype": "bfloat16", "batch_size": 16, "data_dir": [ [ "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/captioning/datacomp/dc1b/stage2", 0.95 ], [ "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/segmentation/sam/stage1", 0.05 ] ], "fd_loss_weight": 1.0, "fd_normalize": false, "feature_distillation": true, "input_size": 378, "match_pre_proj": false, "model": "ViT-H-14-378-quickgelu", "name": "clip", "pretrained": "dfn5b", "sample_rate": 16, "student_resolution": 432, "summary_loss_weight": 1.0, "torchcompile": true, "type": "open_clip", "vitdet_prob": 0.05, "vitdet_window_sizes": [ 3, 9, 9, 9 ] }, { "amp": false, "amp_dtype": "bfloat16", "batch_size": 16, "fd_loss_weight": 0.8, "fd_normalize": false, "feature_distillation": true, "input_size": 336, "match_pre_proj": false, "model": "ViT-L/14@336px", "name": "openai_clip", "pretrained": "openai", "sample_rate": 16, "summary_loss_weight": 0.8, "torchcompile": true, "type": "openai_clip", "use_summary": false }, { "amp": true, "amp_dtype": "bfloat16", "batch_size": 16, "fd_loss_weight": 2.0, "fd_normalize": false, "feature_distillation": true, "input_size": 378, "model": "dinov2_vitg14_reg", "name": "dino_v2", "sample_rate": 16, "summary_loss_weight": 1.0, "torchcompile": true, "type": "dino_v2" }, { "amp": false, "batch_size": 2, "data_dir": [ [ "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/segmentation/sam/stage1", 0.4 ] ], "fd_loss_fn": "MSE", "fd_loss_weight": 0.25, "fd_normalize": false, "fd_ohem": true, "feature_distillation": true, "input_size": 1024, "model": "vit-h", "name": "sam", "sample_rate": 2, "student_resolution": 1024, "summary_loss_weight": 1e-05, "type": "sam", "use_summary": false, "vitdet_prob": 0.99, "vitdet_window_sizes": [ 8, 16, 16 ] }, { "amp": true, "batch_size": 2, "data_dir": [ [ "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/ocr/publaynet/webdataset", 0.4 ], [ "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/ocr/staging/arxiv/hocr", 0.4 ], [ "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/ocr/scene-text/scene-text/text_ocr/webdataset", 0.15 ], [ "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/ocr/scene-text/scene-text/hiertext/webdataset", 0.05 ] ], "fd_loss_fn": "MSE", "fd_loss_weight": 0.13, "fd_normalize": false, "fd_ohem": true, "fd_upsample_factor": 4, "feature_distillation": true, "input_size": 1024, "model": "quality", "name": "rtx-translate", "sample_rate": 2, "student_resolution": 1024, "summary_loss_weight": 1e-05, "type": "rtx_translate", "use_summary": false, "vitdet_prob": 0.99, "vitdet_window_sizes": [ 8, 16, 16 ] } ], "torchcompile": null, "torchscript": false, "train_interpolation": "random", "train_split": "train", "tta": 0, "use_coco": false, "use_multi_epochs_loader": false, "val_data_dir": "/lustre/fsw/portfolios/llmservice/projects/llmservice_nlp_fm/datasets/classification/imagenet-1k/webdataset", "val_ema_only": false, "val_img_size": 432, "val_jobs_script": "run_validation_jobs_vit-h-16.sh", "val_split": "val", "validation_batch_size": 64, "vflip": 0.0, "wandb_entity": "", "wandb_group": "ohem", "wandb_job_type": "", "wandb_name": "", "wandb_project": "", "warmup_epochs": 0.5, "warmup_lr": 1e-05, "warmup_prefix": false, "weight_decay": 0.02, "worker_seeding": "all", "workers": 8, "world_size": 128 }, "auto_map": { "AutoConfig": "configuraion_radio.RADIOConfig", "AutoModel": "modeling_radio.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, "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, "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": [ 432, 432 ], "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": "4.47.1", "typical_p": 1.0, "use_bfloat16": false, "version": "radio_v2.1", "vitdet_window_size": null }, "select_layer": -1, "template": "phi3-chat", "torch_dtype": "bfloat16", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "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, "drop_path_rate": 0.0, "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": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "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-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "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, "pruned_heads": {}, "qk_normalization": false, "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": "bfloat16", "torchscript": false, "transformers_version": "4.47.1", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": true } }