├── .gitignore ├── LICENSE ├── README.md ├── assets ├── logo.png ├── samples.png ├── teaser.png └── vis_imgs │ ├── v0.jpg │ ├── v1.jpg │ ├── v2.jpg │ ├── v3.jpg │ ├── v4.jpg │ ├── v5.jpg │ ├── v6.jpg │ └── v7.jpg ├── eval ├── EVAL.md ├── liquid │ ├── constants.py │ ├── conversation.py │ ├── eval │ │ ├── eval_genai.py │ │ ├── eval_gpt_review.py │ │ ├── eval_gpt_review_bench.py │ │ ├── eval_gpt_review_visual.py │ │ ├── eval_mjhq.py │ │ ├── eval_pope.py │ │ ├── eval_science_qa.py │ │ ├── eval_science_qa_gpt4.py │ │ ├── eval_science_qa_gpt4_requery.py │ │ ├── eval_textvqa.py │ │ ├── generate_webpage_data_from_table.py │ │ ├── infer_genai.py │ │ ├── infer_mjhq.py │ │ ├── m4c_evaluator.py │ │ ├── model_math_vista.py │ │ ├── model_qa.py │ │ ├── model_vqa.py │ │ ├── model_vqa_loader.py │ │ ├── model_vqa_mmbench.py │ │ ├── model_vqa_qbench.py │ │ ├── model_vqa_science.py │ │ ├── qa_baseline_gpt35.py │ │ ├── run_llava.py │ │ └── summarize_gpt_review.py │ ├── mm_utils.py │ ├── model │ │ ├── __init__.py │ │ ├── arhead.py │ │ ├── builder.py │ │ ├── language_model │ │ │ └── mini_gemini_llama.py │ │ ├── liquid.py │ │ ├── multimodal_encoder │ │ │ ├── builder.py │ │ │ ├── clip_encoder.py │ │ │ ├── eva_encoder.py │ │ │ └── openclip_encoder.py │ │ ├── multimodal_projector │ │ │ └── builder.py │ │ ├── processor │ │ │ └── video_processor.py │ │ └── quant.py │ ├── scripts │ │ ├── generation │ │ │ ├── genai.sh │ │ │ └── mjhq.sh │ │ └── understanding │ │ │ ├── convert_gqa_for_eval.py │ │ │ ├── convert_vqav2_for_submission.py │ │ │ ├── gqa.sh │ │ │ ├── mme.sh │ │ │ ├── pope.sh │ │ │ ├── textvqa.sh │ │ │ └── vqav2.sh │ ├── tools.py │ └── train.py ├── llamagen │ ├── autoregressive │ │ ├── __init__.py │ │ ├── models │ │ │ ├── __init__.py │ │ │ ├── generate.py │ │ │ ├── gpt.py │ │ │ └── gpt_hf.py │ │ ├── sample │ │ │ ├── __init__.py │ │ │ ├── sample_c2i.py │ │ │ ├── sample_c2i_ddp.py │ │ │ ├── sample_t2i.py │ │ │ └── sample_t2i_ddp.py │ │ ├── serve │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── fake_json │ │ │ │ ├── GPT-3B.json │ │ │ │ ├── GPT-B.json │ │ │ │ ├── GPT-L.json │ │ │ │ ├── GPT-XL.json │ │ │ │ └── GPT-XXL.json │ │ │ ├── gpt_model.py │ │ │ ├── gpu_executor.py │ │ │ ├── llm.py │ │ │ ├── llm_engine.py │ │ │ ├── model_runner.py │ │ │ ├── sample_c2i.py │ │ │ ├── sampler.py │ │ │ └── worker.py │ │ └── train │ │ │ ├── __init__.py │ │ │ ├── extract_codes_c2i.py │ │ │ ├── extract_codes_t2i.py │ │ │ ├── train_c2i.py │ │ │ ├── train_c2i_fsdp.py │ │ │ └── train_t2i.py │ ├── dataset │ │ ├── __init__.py │ │ ├── augmentation.py │ │ ├── build.py │ │ ├── coco.py │ │ ├── imagenet.py │ │ ├── openimage.py │ │ ├── pexels.py │ │ └── t2i.py │ ├── evaluations │ │ ├── __init__.py │ │ ├── c2i │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ └── evaluator.py │ │ └── t2i │ │ │ ├── PartiPrompts.tsv │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── coco_captions.csv │ │ │ └── evaluation.py │ ├── language │ │ ├── README.md │ │ ├── __init__.py │ │ ├── extract_t5_feature.py │ │ └── t5.py │ ├── scripts │ │ ├── autoregressive │ │ │ ├── extract_codes_c2i.sh │ │ │ ├── sample_c2i.sh │ │ │ ├── sample_t2i_coco.sh │ │ │ ├── sample_t2i_parti.sh │ │ │ ├── train_c2i.sh │ │ │ ├── train_c2i_fsdp.sh │ │ │ ├── train_t2i_stage1.sh │ │ │ └── train_t2i_stage2.sh │ │ ├── language │ │ │ ├── extract_flan_t5_feat_laion_coco_stage1.sh │ │ │ ├── extract_flan_t5_feat_stage2.sh │ │ │ └── extract_flan_t5_feat_trunc_stage2.sh │ │ └── tokenizer │ │ │ ├── reconstruction_consistency_decoder.sh │ │ │ ├── reconstruction_vae.sh │ │ │ ├── reconstruction_vq.sh │ │ │ ├── reconstruction_vqgan.sh │ │ │ ├── train_vq.sh │ │ │ ├── train_vq_finetune.sh │ │ │ ├── train_vq_finetune_continue.sh │ │ │ └── val.sh │ ├── tokenizer │ │ ├── __init__.py │ │ ├── consistencydecoder │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── cd_demo.py │ │ │ └── reconstruction_cd_ddp.py │ │ ├── tokenizer_image │ │ │ ├── __init__.py │ │ │ ├── discriminator.py │ │ │ ├── discriminator_patchgan.py │ │ │ ├── discriminator_stylegan.py │ │ │ ├── lpips.py │ │ │ ├── reconstruction_vq_ddp.py │ │ │ ├── vq_demo.py │ │ │ ├── vq_loss.py │ │ │ ├── vq_model.py │ │ │ ├── vq_model_hf.py │ │ │ └── vq_train.py │ │ ├── vae │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── reconstruction_vae_ddp.py │ │ │ └── sd_vae_demo.py │ │ ├── validation │ │ │ ├── __init__.py │ │ │ └── val_ddp.py │ │ └── vqgan │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── configs │ │ │ ├── vqgan_imagenet_f16_1024.yaml │ │ │ ├── vqgan_imagenet_f16_16384.yaml │ │ │ ├── vqgan_openimage_f8_16384.yaml │ │ │ └── vqgan_openimage_f8_256.yaml │ │ │ ├── layer.py │ │ │ ├── model.py │ │ │ ├── quantize.py │ │ │ ├── reconstruction_vqgan_ddp.py │ │ │ └── taming_vqgan_demo.py │ ├── tools │ │ ├── __init__.py │ │ ├── check_image_codes.py │ │ ├── convert_pytorch_lightning_to_torch.py │ │ ├── draw_figure.py │ │ ├── imagenet_en_cn.py │ │ ├── openimage_json.py │ │ ├── push_gpt_to_hf.py │ │ └── push_vae_to_hf.py │ └── utils │ │ ├── __init__.py │ │ ├── data.py │ │ ├── deepspeed.py │ │ ├── distributed.py │ │ ├── drop_path.py │ │ ├── ema.py │ │ ├── logger.py │ │ └── video.py └── llava │ ├── llava │ ├── __init__.py │ ├── constants.py │ ├── conversation.py │ ├── eval │ │ ├── __init__.py │ │ ├── eval_gpt_review.py │ │ ├── eval_gpt_review_bench.py │ │ ├── eval_gpt_review_visual.py │ │ ├── eval_pope.py │ │ ├── eval_science_qa.py │ │ ├── eval_science_qa_gpt4.py │ │ ├── eval_science_qa_gpt4_requery.py │ │ ├── eval_textvqa.py │ │ ├── generate_webpage_data_from_table.py │ │ ├── m4c_evaluator.py │ │ ├── model_qa.py │ │ ├── model_vqa.py │ │ ├── model_vqa_loader.py │ │ ├── model_vqa_mmbench.py │ │ ├── model_vqa_science.py │ │ ├── qa_baseline_gpt35.py │ │ ├── run_llava.py │ │ ├── summarize_gpt_review.py │ │ ├── table │ │ │ ├── answer │ │ │ │ ├── answer_alpaca-13b.jsonl │ │ │ │ ├── answer_bard.jsonl │ │ │ │ ├── answer_gpt35.jsonl │ │ │ │ ├── answer_llama-13b.jsonl │ │ │ │ └── answer_vicuna-13b.jsonl │ │ │ ├── caps_boxes_coco2014_val_80.jsonl │ │ │ ├── model.jsonl │ │ │ ├── prompt.jsonl │ │ │ ├── question.jsonl │ │ │ ├── results │ │ │ │ ├── test_sqa_llava_13b_v0.json │ │ │ │ └── test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json │ │ │ ├── review │ │ │ │ ├── review_alpaca-13b_vicuna-13b.jsonl │ │ │ │ ├── review_bard_vicuna-13b.jsonl │ │ │ │ ├── review_gpt35_vicuna-13b.jsonl │ │ │ │ └── review_llama-13b_vicuna-13b.jsonl │ │ │ ├── reviewer.jsonl │ │ │ └── rule.json │ │ └── webpage │ │ │ ├── figures │ │ │ ├── alpaca.png │ │ │ ├── bard.jpg │ │ │ ├── chatgpt.svg │ │ │ ├── llama.jpg │ │ │ ├── swords_FILL0_wght300_GRAD0_opsz48.svg │ │ │ └── vicuna.jpeg │ │ │ ├── index.html │ │ │ ├── script.js │ │ │ └── styles.css │ ├── mm_utils.py │ ├── model │ │ ├── __init__.py │ │ ├── apply_delta.py │ │ ├── builder.py │ │ ├── consolidate.py │ │ ├── language_model │ │ │ ├── __init__.py │ │ │ ├── llava_llama.py │ │ │ ├── llava_mistral.py │ │ │ └── llava_mpt.py │ │ ├── llava_arch.py │ │ ├── make_delta.py │ │ ├── multimodal_encoder │ │ │ ├── __init__.py │ │ │ ├── builder.py │ │ │ ├── clip_encoder.py │ │ │ └── unitok_encoder.py │ │ ├── multimodal_projector │ │ │ ├── __init__.py │ │ │ └── builder.py │ │ └── utils.py │ ├── train │ │ ├── __init__.py │ │ ├── llama_flash_attn_monkey_patch.py │ │ ├── llama_xformers_attn_monkey_patch.py │ │ ├── llava_trainer.py │ │ ├── train.py │ │ ├── train_mem.py │ │ └── train_xformers.py │ └── utils.py │ └── scripts │ ├── convert_gqa_for_eval.py │ ├── convert_mmbench_for_submission.py │ ├── convert_mmvet_for_eval.py │ ├── convert_seed_for_submission.py │ ├── convert_sqa_to_llava.py │ ├── convert_sqa_to_llava_base_prompt.py │ ├── convert_vizwiz_for_submission.py │ ├── convert_vqav2_for_submission.py │ ├── extract_mm_projector.py │ ├── finetune.sh │ ├── finetune_full_schedule.sh │ ├── finetune_lora.sh │ ├── finetune_qlora.sh │ ├── finetune_sqa.sh │ ├── merge_lora_weights.py │ ├── pretrain.sh │ ├── pretrain_xformers.sh │ ├── sqa_eval_batch.sh │ ├── sqa_eval_gather.sh │ ├── upload_pypi.sh │ ├── v1_5 │ ├── eval │ │ ├── gqa.sh │ │ ├── llavabench.sh │ │ ├── mmbench.sh │ │ ├── mmbench_cn.sh │ │ ├── mme.sh │ │ ├── mmvet.sh │ │ ├── pope.sh │ │ ├── qbench.sh │ │ ├── qbench_zh.sh │ │ ├── seed.sh │ │ ├── sqa.sh │ │ ├── textvqa.sh │ │ ├── vizwiz.sh │ │ └── vqav2.sh │ ├── finetune.sh │ ├── finetune_lora.sh │ ├── finetune_task.sh │ ├── finetune_task_lora.sh │ └── pretrain.sh │ ├── zero2.json │ ├── zero3.json │ └── zero3_offload.json ├── inference.py ├── launch.sh ├── main.py ├── models ├── __init__.py ├── dinov2.py ├── discrim.py ├── layers │ ├── __init__.py │ ├── attention.py │ ├── block.py │ ├── dino_head.py │ ├── drop_path.py │ ├── layer_scale.py │ ├── mlp.py │ ├── patch_embed.py │ └── swiglu_ffn.py ├── quant.py ├── unitok.py ├── vitamin.py └── vqvae.py ├── open_clip ├── __init__.py ├── bpe_simple_vocab_16e6.txt.gz ├── coca_model.py ├── constants.py ├── factory.py ├── generation_utils.py ├── hf_configs.py ├── hf_model.py ├── loss.py ├── model.py ├── model_configs │ ├── TiTok-B.json │ ├── ViT-B-16-T768.json │ ├── ViT-B-16.json │ ├── ViT-B-32.json │ ├── ViT-H-14-336.json │ ├── ViT-H-14.json │ ├── ViT-H-16.json │ ├── ViT-L-14-336.json │ ├── ViT-L-14.json │ ├── ViT-L-16.json │ ├── ViT-L-32.json │ ├── ViT-S-16.json │ ├── ViT-S-32.json │ ├── ViTamin-B-256.json │ ├── ViTamin-B-T768.json │ ├── ViTamin-B.json │ ├── ViTamin-L-256.json │ ├── ViTamin-L-336.json │ ├── ViTamin-L-384.json │ ├── ViTamin-L.json │ ├── ViTamin-L2-256.json │ ├── ViTamin-L2-336.json │ ├── ViTamin-L2-384.json │ ├── ViTamin-L2.json │ ├── ViTamin-S-T768.json │ ├── ViTamin-S.json │ ├── ViTamin-XL-256.json │ ├── ViTamin-XL-336.json │ ├── ViTamin-XL-384.json │ ├── ViTamin-XL.json │ ├── coatnet_0.json │ ├── coatnet_2.json │ ├── coatnet_4.json │ ├── convnext_base.json │ ├── convnext_small.json │ ├── convnext_tiny_d384.json │ ├── convnext_xlarge.json │ └── convnext_xlarge_t768.json ├── modified_resnet.py ├── openai.py ├── pretrained.py ├── push_to_hf_hub.py ├── timm_model.py ├── tokenizer.py ├── transform.py ├── transformer.py ├── utils.py ├── version.py ├── zero_shot_classifier.py └── zero_shot_metadata.py ├── requirements.txt ├── trainer.py └── utils ├── __init__.py ├── config.py ├── data.py ├── diffaug.py ├── dist.py ├── eval_acc.py ├── eval_fid.py ├── logger.py ├── loss.py ├── lpips.py ├── misc.py ├── nan.py ├── optimizer.py ├── sampler.py ├── scheduler.py └── visualizer.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/README.md -------------------------------------------------------------------------------- /assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/logo.png -------------------------------------------------------------------------------- /assets/samples.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/samples.png -------------------------------------------------------------------------------- /assets/teaser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/teaser.png -------------------------------------------------------------------------------- /assets/vis_imgs/v0.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/vis_imgs/v0.jpg -------------------------------------------------------------------------------- /assets/vis_imgs/v1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/vis_imgs/v1.jpg -------------------------------------------------------------------------------- /assets/vis_imgs/v2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/vis_imgs/v2.jpg -------------------------------------------------------------------------------- /assets/vis_imgs/v3.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/vis_imgs/v3.jpg -------------------------------------------------------------------------------- /assets/vis_imgs/v4.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/vis_imgs/v4.jpg -------------------------------------------------------------------------------- /assets/vis_imgs/v5.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/vis_imgs/v5.jpg -------------------------------------------------------------------------------- /assets/vis_imgs/v6.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/vis_imgs/v6.jpg -------------------------------------------------------------------------------- /assets/vis_imgs/v7.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/assets/vis_imgs/v7.jpg -------------------------------------------------------------------------------- /eval/EVAL.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/EVAL.md -------------------------------------------------------------------------------- /eval/liquid/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/constants.py -------------------------------------------------------------------------------- /eval/liquid/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/conversation.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_genai.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_genai.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_gpt_review.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_gpt_review.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_gpt_review_bench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_gpt_review_bench.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_gpt_review_visual.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_gpt_review_visual.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_mjhq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_mjhq.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_pope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_pope.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_science_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_science_qa.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_science_qa_gpt4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_science_qa_gpt4.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_science_qa_gpt4_requery.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_science_qa_gpt4_requery.py -------------------------------------------------------------------------------- /eval/liquid/eval/eval_textvqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/eval_textvqa.py -------------------------------------------------------------------------------- /eval/liquid/eval/generate_webpage_data_from_table.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/generate_webpage_data_from_table.py -------------------------------------------------------------------------------- /eval/liquid/eval/infer_genai.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/infer_genai.py -------------------------------------------------------------------------------- /eval/liquid/eval/infer_mjhq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/infer_mjhq.py -------------------------------------------------------------------------------- /eval/liquid/eval/m4c_evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/m4c_evaluator.py -------------------------------------------------------------------------------- /eval/liquid/eval/model_math_vista.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/model_math_vista.py -------------------------------------------------------------------------------- /eval/liquid/eval/model_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/model_qa.py -------------------------------------------------------------------------------- /eval/liquid/eval/model_vqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/model_vqa.py -------------------------------------------------------------------------------- /eval/liquid/eval/model_vqa_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/model_vqa_loader.py -------------------------------------------------------------------------------- /eval/liquid/eval/model_vqa_mmbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/model_vqa_mmbench.py -------------------------------------------------------------------------------- /eval/liquid/eval/model_vqa_qbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/model_vqa_qbench.py -------------------------------------------------------------------------------- /eval/liquid/eval/model_vqa_science.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/model_vqa_science.py -------------------------------------------------------------------------------- /eval/liquid/eval/qa_baseline_gpt35.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/qa_baseline_gpt35.py -------------------------------------------------------------------------------- /eval/liquid/eval/run_llava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/run_llava.py -------------------------------------------------------------------------------- /eval/liquid/eval/summarize_gpt_review.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/eval/summarize_gpt_review.py -------------------------------------------------------------------------------- /eval/liquid/mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/mm_utils.py -------------------------------------------------------------------------------- /eval/liquid/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/__init__.py -------------------------------------------------------------------------------- /eval/liquid/model/arhead.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/arhead.py -------------------------------------------------------------------------------- /eval/liquid/model/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/builder.py -------------------------------------------------------------------------------- /eval/liquid/model/language_model/mini_gemini_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/language_model/mini_gemini_llama.py -------------------------------------------------------------------------------- /eval/liquid/model/liquid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/liquid.py -------------------------------------------------------------------------------- /eval/liquid/model/multimodal_encoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/multimodal_encoder/builder.py -------------------------------------------------------------------------------- /eval/liquid/model/multimodal_encoder/clip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/multimodal_encoder/clip_encoder.py -------------------------------------------------------------------------------- /eval/liquid/model/multimodal_encoder/eva_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/multimodal_encoder/eva_encoder.py -------------------------------------------------------------------------------- /eval/liquid/model/multimodal_encoder/openclip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/multimodal_encoder/openclip_encoder.py -------------------------------------------------------------------------------- /eval/liquid/model/multimodal_projector/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/multimodal_projector/builder.py -------------------------------------------------------------------------------- /eval/liquid/model/processor/video_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/processor/video_processor.py -------------------------------------------------------------------------------- /eval/liquid/model/quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/model/quant.py -------------------------------------------------------------------------------- /eval/liquid/scripts/generation/genai.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/scripts/generation/genai.sh -------------------------------------------------------------------------------- /eval/liquid/scripts/generation/mjhq.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/scripts/generation/mjhq.sh -------------------------------------------------------------------------------- /eval/liquid/scripts/understanding/convert_gqa_for_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/scripts/understanding/convert_gqa_for_eval.py -------------------------------------------------------------------------------- /eval/liquid/scripts/understanding/convert_vqav2_for_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/scripts/understanding/convert_vqav2_for_submission.py -------------------------------------------------------------------------------- /eval/liquid/scripts/understanding/gqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/scripts/understanding/gqa.sh -------------------------------------------------------------------------------- /eval/liquid/scripts/understanding/mme.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/scripts/understanding/mme.sh -------------------------------------------------------------------------------- /eval/liquid/scripts/understanding/pope.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/scripts/understanding/pope.sh -------------------------------------------------------------------------------- /eval/liquid/scripts/understanding/textvqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/scripts/understanding/textvqa.sh -------------------------------------------------------------------------------- /eval/liquid/scripts/understanding/vqav2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/scripts/understanding/vqav2.sh -------------------------------------------------------------------------------- /eval/liquid/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/tools.py -------------------------------------------------------------------------------- /eval/liquid/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/liquid/train.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/models/generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/models/generate.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/models/gpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/models/gpt.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/models/gpt_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/models/gpt_hf.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/sample/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/sample/sample_c2i.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/sample/sample_c2i.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/sample/sample_c2i_ddp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/sample/sample_c2i_ddp.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/sample/sample_t2i.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/sample/sample_t2i.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/sample/sample_t2i_ddp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/sample/sample_t2i_ddp.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/README.md -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/fake_json/GPT-3B.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/fake_json/GPT-3B.json -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/fake_json/GPT-B.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/fake_json/GPT-B.json -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/fake_json/GPT-L.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/fake_json/GPT-L.json -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/fake_json/GPT-XL.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/fake_json/GPT-XL.json -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/fake_json/GPT-XXL.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/fake_json/GPT-XXL.json -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/gpt_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/gpt_model.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/gpu_executor.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/llm.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/llm_engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/llm_engine.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/model_runner.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/sample_c2i.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/sample_c2i.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/sampler.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/serve/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/serve/worker.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/train/extract_codes_c2i.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/train/extract_codes_c2i.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/train/extract_codes_t2i.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/train/extract_codes_t2i.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/train/train_c2i.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/train/train_c2i.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/train/train_c2i_fsdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/train/train_c2i_fsdp.py -------------------------------------------------------------------------------- /eval/llamagen/autoregressive/train/train_t2i.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/autoregressive/train/train_t2i.py -------------------------------------------------------------------------------- /eval/llamagen/dataset/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/dataset/augmentation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/dataset/augmentation.py -------------------------------------------------------------------------------- /eval/llamagen/dataset/build.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/dataset/build.py -------------------------------------------------------------------------------- /eval/llamagen/dataset/coco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/dataset/coco.py -------------------------------------------------------------------------------- /eval/llamagen/dataset/imagenet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/dataset/imagenet.py -------------------------------------------------------------------------------- /eval/llamagen/dataset/openimage.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/dataset/openimage.py -------------------------------------------------------------------------------- /eval/llamagen/dataset/pexels.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/dataset/pexels.py -------------------------------------------------------------------------------- /eval/llamagen/dataset/t2i.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/dataset/t2i.py -------------------------------------------------------------------------------- /eval/llamagen/evaluations/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/evaluations/c2i/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/evaluations/c2i/README.md -------------------------------------------------------------------------------- /eval/llamagen/evaluations/c2i/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/evaluations/c2i/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/evaluations/c2i/evaluator.py -------------------------------------------------------------------------------- /eval/llamagen/evaluations/t2i/PartiPrompts.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/evaluations/t2i/PartiPrompts.tsv -------------------------------------------------------------------------------- /eval/llamagen/evaluations/t2i/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/evaluations/t2i/README.md -------------------------------------------------------------------------------- /eval/llamagen/evaluations/t2i/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/evaluations/t2i/coco_captions.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/evaluations/t2i/coco_captions.csv -------------------------------------------------------------------------------- /eval/llamagen/evaluations/t2i/evaluation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/evaluations/t2i/evaluation.py -------------------------------------------------------------------------------- /eval/llamagen/language/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/language/README.md -------------------------------------------------------------------------------- /eval/llamagen/language/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/language/extract_t5_feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/language/extract_t5_feature.py -------------------------------------------------------------------------------- /eval/llamagen/language/t5.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/language/t5.py -------------------------------------------------------------------------------- /eval/llamagen/scripts/autoregressive/extract_codes_c2i.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/autoregressive/extract_codes_c2i.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/autoregressive/sample_c2i.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/autoregressive/sample_c2i.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/autoregressive/sample_t2i_coco.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/autoregressive/sample_t2i_coco.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/autoregressive/sample_t2i_parti.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/autoregressive/sample_t2i_parti.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/autoregressive/train_c2i.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/autoregressive/train_c2i.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/autoregressive/train_c2i_fsdp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/autoregressive/train_c2i_fsdp.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/autoregressive/train_t2i_stage1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/autoregressive/train_t2i_stage1.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/autoregressive/train_t2i_stage2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/autoregressive/train_t2i_stage2.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/language/extract_flan_t5_feat_laion_coco_stage1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/language/extract_flan_t5_feat_laion_coco_stage1.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/language/extract_flan_t5_feat_stage2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/language/extract_flan_t5_feat_stage2.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/language/extract_flan_t5_feat_trunc_stage2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/language/extract_flan_t5_feat_trunc_stage2.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/tokenizer/reconstruction_consistency_decoder.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/tokenizer/reconstruction_consistency_decoder.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/tokenizer/reconstruction_vae.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/tokenizer/reconstruction_vae.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/tokenizer/reconstruction_vq.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/tokenizer/reconstruction_vq.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/tokenizer/reconstruction_vqgan.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/tokenizer/reconstruction_vqgan.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/tokenizer/train_vq.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/tokenizer/train_vq.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/tokenizer/train_vq_finetune.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/tokenizer/train_vq_finetune.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/tokenizer/train_vq_finetune_continue.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/tokenizer/train_vq_finetune_continue.sh -------------------------------------------------------------------------------- /eval/llamagen/scripts/tokenizer/val.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/scripts/tokenizer/val.sh -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/consistencydecoder/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/consistencydecoder/README.md -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/consistencydecoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/consistencydecoder/cd_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/consistencydecoder/cd_demo.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/consistencydecoder/reconstruction_cd_ddp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/consistencydecoder/reconstruction_cd_ddp.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/discriminator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/discriminator.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/discriminator_patchgan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/discriminator_patchgan.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/discriminator_stylegan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/discriminator_stylegan.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/lpips.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/lpips.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/reconstruction_vq_ddp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/reconstruction_vq_ddp.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/vq_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/vq_demo.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/vq_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/vq_loss.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/vq_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/vq_model.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/vq_model_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/vq_model_hf.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/tokenizer_image/vq_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/tokenizer_image/vq_train.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vae/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vae/README.md -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vae/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vae/reconstruction_vae_ddp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vae/reconstruction_vae_ddp.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vae/sd_vae_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vae/sd_vae_demo.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/validation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/validation/val_ddp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/validation/val_ddp.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/README.md -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/configs/vqgan_imagenet_f16_1024.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/configs/vqgan_imagenet_f16_1024.yaml -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/configs/vqgan_imagenet_f16_16384.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/configs/vqgan_imagenet_f16_16384.yaml -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/configs/vqgan_openimage_f8_16384.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/configs/vqgan_openimage_f8_16384.yaml -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/configs/vqgan_openimage_f8_256.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/configs/vqgan_openimage_f8_256.yaml -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/layer.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/model.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/quantize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/quantize.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/reconstruction_vqgan_ddp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/reconstruction_vqgan_ddp.py -------------------------------------------------------------------------------- /eval/llamagen/tokenizer/vqgan/taming_vqgan_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tokenizer/vqgan/taming_vqgan_demo.py -------------------------------------------------------------------------------- /eval/llamagen/tools/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/tools/check_image_codes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tools/check_image_codes.py -------------------------------------------------------------------------------- /eval/llamagen/tools/convert_pytorch_lightning_to_torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tools/convert_pytorch_lightning_to_torch.py -------------------------------------------------------------------------------- /eval/llamagen/tools/draw_figure.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tools/draw_figure.py -------------------------------------------------------------------------------- /eval/llamagen/tools/imagenet_en_cn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tools/imagenet_en_cn.py -------------------------------------------------------------------------------- /eval/llamagen/tools/openimage_json.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tools/openimage_json.py -------------------------------------------------------------------------------- /eval/llamagen/tools/push_gpt_to_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tools/push_gpt_to_hf.py -------------------------------------------------------------------------------- /eval/llamagen/tools/push_vae_to_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/tools/push_vae_to_hf.py -------------------------------------------------------------------------------- /eval/llamagen/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llamagen/utils/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/utils/data.py -------------------------------------------------------------------------------- /eval/llamagen/utils/deepspeed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/utils/deepspeed.py -------------------------------------------------------------------------------- /eval/llamagen/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/utils/distributed.py -------------------------------------------------------------------------------- /eval/llamagen/utils/drop_path.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/utils/drop_path.py -------------------------------------------------------------------------------- /eval/llamagen/utils/ema.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/utils/ema.py -------------------------------------------------------------------------------- /eval/llamagen/utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/utils/logger.py -------------------------------------------------------------------------------- /eval/llamagen/utils/video.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llamagen/utils/video.py -------------------------------------------------------------------------------- /eval/llava/llava/__init__.py: -------------------------------------------------------------------------------- 1 | from .model import LlavaLlamaForCausalLM 2 | -------------------------------------------------------------------------------- /eval/llava/llava/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/constants.py -------------------------------------------------------------------------------- /eval/llava/llava/conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/conversation.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llava/llava/eval/eval_gpt_review.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/eval_gpt_review.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/eval_gpt_review_bench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/eval_gpt_review_bench.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/eval_gpt_review_visual.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/eval_gpt_review_visual.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/eval_pope.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/eval_pope.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/eval_science_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/eval_science_qa.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/eval_science_qa_gpt4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/eval_science_qa_gpt4.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/eval_science_qa_gpt4_requery.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/eval_science_qa_gpt4_requery.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/eval_textvqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/eval_textvqa.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/generate_webpage_data_from_table.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/generate_webpage_data_from_table.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/m4c_evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/m4c_evaluator.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/model_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/model_qa.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/model_vqa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/model_vqa.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/model_vqa_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/model_vqa_loader.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/model_vqa_mmbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/model_vqa_mmbench.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/model_vqa_science.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/model_vqa_science.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/qa_baseline_gpt35.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/qa_baseline_gpt35.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/run_llava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/run_llava.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/summarize_gpt_review.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/summarize_gpt_review.py -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/answer/answer_alpaca-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/answer/answer_alpaca-13b.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/answer/answer_bard.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/answer/answer_bard.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/answer/answer_gpt35.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/answer/answer_gpt35.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/answer/answer_llama-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/answer/answer_llama-13b.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/answer/answer_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/answer/answer_vicuna-13b.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/caps_boxes_coco2014_val_80.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/caps_boxes_coco2014_val_80.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/model.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/model.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/prompt.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/prompt.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/question.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/question.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/results/test_sqa_llava_13b_v0.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/results/test_sqa_llava_13b_v0.json -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/results/test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/results/test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/review/review_alpaca-13b_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/review/review_alpaca-13b_vicuna-13b.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/review/review_bard_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/review/review_bard_vicuna-13b.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/review/review_gpt35_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/review/review_gpt35_vicuna-13b.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/review/review_llama-13b_vicuna-13b.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/review/review_llama-13b_vicuna-13b.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/reviewer.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/reviewer.jsonl -------------------------------------------------------------------------------- /eval/llava/llava/eval/table/rule.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/table/rule.json -------------------------------------------------------------------------------- /eval/llava/llava/eval/webpage/figures/alpaca.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/webpage/figures/alpaca.png -------------------------------------------------------------------------------- /eval/llava/llava/eval/webpage/figures/bard.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/webpage/figures/bard.jpg -------------------------------------------------------------------------------- /eval/llava/llava/eval/webpage/figures/chatgpt.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/webpage/figures/chatgpt.svg -------------------------------------------------------------------------------- /eval/llava/llava/eval/webpage/figures/llama.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/webpage/figures/llama.jpg -------------------------------------------------------------------------------- /eval/llava/llava/eval/webpage/figures/swords_FILL0_wght300_GRAD0_opsz48.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/webpage/figures/swords_FILL0_wght300_GRAD0_opsz48.svg -------------------------------------------------------------------------------- /eval/llava/llava/eval/webpage/figures/vicuna.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/webpage/figures/vicuna.jpeg -------------------------------------------------------------------------------- /eval/llava/llava/eval/webpage/index.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/webpage/index.html -------------------------------------------------------------------------------- /eval/llava/llava/eval/webpage/script.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/webpage/script.js -------------------------------------------------------------------------------- /eval/llava/llava/eval/webpage/styles.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/eval/webpage/styles.css -------------------------------------------------------------------------------- /eval/llava/llava/mm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/mm_utils.py -------------------------------------------------------------------------------- /eval/llava/llava/model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/__init__.py -------------------------------------------------------------------------------- /eval/llava/llava/model/apply_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/apply_delta.py -------------------------------------------------------------------------------- /eval/llava/llava/model/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/builder.py -------------------------------------------------------------------------------- /eval/llava/llava/model/consolidate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/consolidate.py -------------------------------------------------------------------------------- /eval/llava/llava/model/language_model/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llava/llava/model/language_model/llava_llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/language_model/llava_llama.py -------------------------------------------------------------------------------- /eval/llava/llava/model/language_model/llava_mistral.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/language_model/llava_mistral.py -------------------------------------------------------------------------------- /eval/llava/llava/model/language_model/llava_mpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/language_model/llava_mpt.py -------------------------------------------------------------------------------- /eval/llava/llava/model/llava_arch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/llava_arch.py -------------------------------------------------------------------------------- /eval/llava/llava/model/make_delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/make_delta.py -------------------------------------------------------------------------------- /eval/llava/llava/model/multimodal_encoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llava/llava/model/multimodal_encoder/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/multimodal_encoder/builder.py -------------------------------------------------------------------------------- /eval/llava/llava/model/multimodal_encoder/clip_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/multimodal_encoder/clip_encoder.py -------------------------------------------------------------------------------- /eval/llava/llava/model/multimodal_encoder/unitok_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/multimodal_encoder/unitok_encoder.py -------------------------------------------------------------------------------- /eval/llava/llava/model/multimodal_projector/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llava/llava/model/multimodal_projector/builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/multimodal_projector/builder.py -------------------------------------------------------------------------------- /eval/llava/llava/model/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/model/utils.py -------------------------------------------------------------------------------- /eval/llava/llava/train/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eval/llava/llava/train/llama_flash_attn_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/train/llama_flash_attn_monkey_patch.py -------------------------------------------------------------------------------- /eval/llava/llava/train/llama_xformers_attn_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/train/llama_xformers_attn_monkey_patch.py -------------------------------------------------------------------------------- /eval/llava/llava/train/llava_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/train/llava_trainer.py -------------------------------------------------------------------------------- /eval/llava/llava/train/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/train/train.py -------------------------------------------------------------------------------- /eval/llava/llava/train/train_mem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/train/train_mem.py -------------------------------------------------------------------------------- /eval/llava/llava/train/train_xformers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/train/train_xformers.py -------------------------------------------------------------------------------- /eval/llava/llava/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/llava/utils.py -------------------------------------------------------------------------------- /eval/llava/scripts/convert_gqa_for_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/convert_gqa_for_eval.py -------------------------------------------------------------------------------- /eval/llava/scripts/convert_mmbench_for_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/convert_mmbench_for_submission.py -------------------------------------------------------------------------------- /eval/llava/scripts/convert_mmvet_for_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/convert_mmvet_for_eval.py -------------------------------------------------------------------------------- /eval/llava/scripts/convert_seed_for_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/convert_seed_for_submission.py -------------------------------------------------------------------------------- /eval/llava/scripts/convert_sqa_to_llava.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/convert_sqa_to_llava.py -------------------------------------------------------------------------------- /eval/llava/scripts/convert_sqa_to_llava_base_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/convert_sqa_to_llava_base_prompt.py -------------------------------------------------------------------------------- /eval/llava/scripts/convert_vizwiz_for_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/convert_vizwiz_for_submission.py -------------------------------------------------------------------------------- /eval/llava/scripts/convert_vqav2_for_submission.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/convert_vqav2_for_submission.py -------------------------------------------------------------------------------- /eval/llava/scripts/extract_mm_projector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/extract_mm_projector.py -------------------------------------------------------------------------------- /eval/llava/scripts/finetune.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/finetune.sh -------------------------------------------------------------------------------- /eval/llava/scripts/finetune_full_schedule.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/finetune_full_schedule.sh -------------------------------------------------------------------------------- /eval/llava/scripts/finetune_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/finetune_lora.sh -------------------------------------------------------------------------------- /eval/llava/scripts/finetune_qlora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/finetune_qlora.sh -------------------------------------------------------------------------------- /eval/llava/scripts/finetune_sqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/finetune_sqa.sh -------------------------------------------------------------------------------- /eval/llava/scripts/merge_lora_weights.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/merge_lora_weights.py -------------------------------------------------------------------------------- /eval/llava/scripts/pretrain.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/pretrain.sh -------------------------------------------------------------------------------- /eval/llava/scripts/pretrain_xformers.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/pretrain_xformers.sh -------------------------------------------------------------------------------- /eval/llava/scripts/sqa_eval_batch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/sqa_eval_batch.sh -------------------------------------------------------------------------------- /eval/llava/scripts/sqa_eval_gather.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/sqa_eval_gather.sh -------------------------------------------------------------------------------- /eval/llava/scripts/upload_pypi.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/upload_pypi.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/gqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/gqa.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/llavabench.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/llavabench.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/mmbench.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/mmbench.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/mmbench_cn.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/mmbench_cn.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/mme.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/mme.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/mmvet.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/mmvet.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/pope.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/pope.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/qbench.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/qbench.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/qbench_zh.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/qbench_zh.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/seed.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/seed.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/sqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/sqa.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/textvqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/textvqa.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/vizwiz.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/vizwiz.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/eval/vqav2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/eval/vqav2.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/finetune.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/finetune.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/finetune_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/finetune_lora.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/finetune_task.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/finetune_task.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/finetune_task_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/finetune_task_lora.sh -------------------------------------------------------------------------------- /eval/llava/scripts/v1_5/pretrain.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/v1_5/pretrain.sh -------------------------------------------------------------------------------- /eval/llava/scripts/zero2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/zero2.json -------------------------------------------------------------------------------- /eval/llava/scripts/zero3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/zero3.json -------------------------------------------------------------------------------- /eval/llava/scripts/zero3_offload.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/eval/llava/scripts/zero3_offload.json -------------------------------------------------------------------------------- /inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/inference.py -------------------------------------------------------------------------------- /launch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/launch.sh -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/main.py -------------------------------------------------------------------------------- /models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/__init__.py -------------------------------------------------------------------------------- /models/dinov2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/dinov2.py -------------------------------------------------------------------------------- /models/discrim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/discrim.py -------------------------------------------------------------------------------- /models/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/layers/__init__.py -------------------------------------------------------------------------------- /models/layers/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/layers/attention.py -------------------------------------------------------------------------------- /models/layers/block.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/layers/block.py -------------------------------------------------------------------------------- /models/layers/dino_head.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/layers/dino_head.py -------------------------------------------------------------------------------- /models/layers/drop_path.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/layers/drop_path.py -------------------------------------------------------------------------------- /models/layers/layer_scale.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/layers/layer_scale.py -------------------------------------------------------------------------------- /models/layers/mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/layers/mlp.py -------------------------------------------------------------------------------- /models/layers/patch_embed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/layers/patch_embed.py -------------------------------------------------------------------------------- /models/layers/swiglu_ffn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/layers/swiglu_ffn.py -------------------------------------------------------------------------------- /models/quant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/quant.py -------------------------------------------------------------------------------- /models/unitok.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/unitok.py -------------------------------------------------------------------------------- /models/vitamin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/vitamin.py -------------------------------------------------------------------------------- /models/vqvae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/models/vqvae.py -------------------------------------------------------------------------------- /open_clip/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/__init__.py -------------------------------------------------------------------------------- /open_clip/bpe_simple_vocab_16e6.txt.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/bpe_simple_vocab_16e6.txt.gz -------------------------------------------------------------------------------- /open_clip/coca_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/coca_model.py -------------------------------------------------------------------------------- /open_clip/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/constants.py -------------------------------------------------------------------------------- /open_clip/factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/factory.py -------------------------------------------------------------------------------- /open_clip/generation_utils.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /open_clip/hf_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/hf_configs.py -------------------------------------------------------------------------------- /open_clip/hf_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/hf_model.py -------------------------------------------------------------------------------- /open_clip/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/loss.py -------------------------------------------------------------------------------- /open_clip/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model.py -------------------------------------------------------------------------------- /open_clip/model_configs/TiTok-B.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/TiTok-B.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-B-16-T768.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-B-16-T768.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-B-16.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-B-16.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-B-32.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-B-32.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-H-14-336.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-H-14-336.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-H-14.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-H-14.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-H-16.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-H-16.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-L-14-336.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-L-14-336.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-L-14.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-L-14.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-L-16.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-L-16.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-L-32.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-L-32.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-S-16.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-S-16.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViT-S-32.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViT-S-32.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-B-256.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-B-256.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-B-T768.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-B-T768.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-B.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-B.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-L-256.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-L-256.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-L-336.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-L-336.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-L-384.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-L-384.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-L.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-L.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-L2-256.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-L2-256.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-L2-336.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-L2-336.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-L2-384.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-L2-384.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-L2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-L2.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-S-T768.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-S-T768.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-S.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-S.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-XL-256.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-XL-256.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-XL-336.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-XL-336.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-XL-384.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-XL-384.json -------------------------------------------------------------------------------- /open_clip/model_configs/ViTamin-XL.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/ViTamin-XL.json -------------------------------------------------------------------------------- /open_clip/model_configs/coatnet_0.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/coatnet_0.json -------------------------------------------------------------------------------- /open_clip/model_configs/coatnet_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/coatnet_2.json -------------------------------------------------------------------------------- /open_clip/model_configs/coatnet_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/coatnet_4.json -------------------------------------------------------------------------------- /open_clip/model_configs/convnext_base.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/convnext_base.json -------------------------------------------------------------------------------- /open_clip/model_configs/convnext_small.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/convnext_small.json -------------------------------------------------------------------------------- /open_clip/model_configs/convnext_tiny_d384.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/convnext_tiny_d384.json -------------------------------------------------------------------------------- /open_clip/model_configs/convnext_xlarge.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/convnext_xlarge.json -------------------------------------------------------------------------------- /open_clip/model_configs/convnext_xlarge_t768.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/model_configs/convnext_xlarge_t768.json -------------------------------------------------------------------------------- /open_clip/modified_resnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/modified_resnet.py -------------------------------------------------------------------------------- /open_clip/openai.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/openai.py -------------------------------------------------------------------------------- /open_clip/pretrained.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/pretrained.py -------------------------------------------------------------------------------- /open_clip/push_to_hf_hub.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/push_to_hf_hub.py -------------------------------------------------------------------------------- /open_clip/timm_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/timm_model.py -------------------------------------------------------------------------------- /open_clip/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/tokenizer.py -------------------------------------------------------------------------------- /open_clip/transform.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/transform.py -------------------------------------------------------------------------------- /open_clip/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/transformer.py -------------------------------------------------------------------------------- /open_clip/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/utils.py -------------------------------------------------------------------------------- /open_clip/version.py: -------------------------------------------------------------------------------- 1 | __version__ = '2.20.0' 2 | -------------------------------------------------------------------------------- /open_clip/zero_shot_classifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/zero_shot_classifier.py -------------------------------------------------------------------------------- /open_clip/zero_shot_metadata.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/open_clip/zero_shot_metadata.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/requirements.txt -------------------------------------------------------------------------------- /trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/trainer.py -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/config.py -------------------------------------------------------------------------------- /utils/data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/data.py -------------------------------------------------------------------------------- /utils/diffaug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/diffaug.py -------------------------------------------------------------------------------- /utils/dist.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/dist.py -------------------------------------------------------------------------------- /utils/eval_acc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/eval_acc.py -------------------------------------------------------------------------------- /utils/eval_fid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/eval_fid.py -------------------------------------------------------------------------------- /utils/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/logger.py -------------------------------------------------------------------------------- /utils/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/loss.py -------------------------------------------------------------------------------- /utils/lpips.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/lpips.py -------------------------------------------------------------------------------- /utils/misc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/misc.py -------------------------------------------------------------------------------- /utils/nan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/nan.py -------------------------------------------------------------------------------- /utils/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/optimizer.py -------------------------------------------------------------------------------- /utils/sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/sampler.py -------------------------------------------------------------------------------- /utils/scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/scheduler.py -------------------------------------------------------------------------------- /utils/visualizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/FoundationVision/UniTok/HEAD/utils/visualizer.py --------------------------------------------------------------------------------