V-DPO
Preference Learning for LLaVA
파일 탐색기
최종 버전 다운로드 (.zip)- deepspeed_config.py
- ds_eval_config_template.json
- ds_train_config_template.json
- answer_alpaca-13b.jsonl
- answer_bard.jsonl
- answer_gpt35.jsonl
- answer_llama-13b.jsonl
- answer_vicuna-13b.jsonl
- test_sqa_llava_13b_v0.json
- test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json
- review_alpaca-13b_vicuna-13b.jsonl
- review_bard_vicuna-13b.jsonl
- review_gpt35_vicuna-13b.jsonl
- review_llama-13b_vicuna-13b.jsonl
- caps_boxes_coco2014_val_80.jsonl
- model.jsonl
- prompt.jsonl
- question.jsonl
- reviewer.jsonl
- rule.json
- alpaca.png
- bard.jpg
- chatgpt.svg
- llama.jpg
- swords_FILL0_wght300_GRAD0_opsz48.svg
- vicuna.jpeg
- index.html
- script.js
- styles.css
- 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
- faithscore_eval.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_qbench.py
- model_vqa_science.py
- qa_baseline_gpt35.py
- run_llava.py
- summarize_gpt_review.py
- adapt_tokenizer.py
- attention.py
- blocks.py
- configuration_mpt.py
- custom_embedding.py
- flash_attn_triton.py
- hf_prefixlm_converter.py
- meta_init_context.py
- modeling_mpt.py
- norm.py
- param_init_fns.py
- llava_llama.py
- llava_mpt.py
- builder.py
- clip_encoder.py
- builder.py
- __init__.py
- apply_delta.py
- builder.py
- consolidate.py
- llava_arch.py
- make_delta.py
- utils.py
- extreme_ironing.jpg
- waterview.jpg
- __init__.py
- cli.py
- controller.py
- gradio_web_server.py
- model_worker.py
- register_worker.py
- test_message.py
- dpo_train.py
- llama_flash_attn_monkey_patch.py
- llama_xformers_attn_monkey_patch.py
- llava_trainer.py
- train.py
- train_mem.py
- train_xformers.py
- __init__.py
- constants.py
- conversation.py
- logger.py
- mm_utils.py
- utils.py
- qa90_gpt4_answer.jsonl
- qa90_questions.jsonl
- coco_pope_adversarial.json
- coco_pope_all.json
- coco_pope_popular.json
- coco_pope_random.json
- 000_caps.txt
- 000_conv.txt
- 001_caps.txt
- 001_conv.txt
- 002_caps.txt
- 002_conv.txt
- system_message.txt
- 000_caps.txt
- 000_conv.txt
- 001_caps.txt
- 001_conv.txt
- system_message.txt
- 000_caps.txt
- 000_conv.txt
- 001_caps.txt
- 001_conv.txt
- 002_caps.txt
- 002_conv.txt
- system_message.txt
- amber_query.jsonl
- coco2014_val_gpt4_qa_30x3.jsonl
- pope.jsonl
- dpo.sh
- vdpo.sh
- 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
- zero2.json
- zero3.json
- zero3_offload.json
- zero3_offload_all.json
- .gitignore
- LICENSE
- llava.md
- llava_dpo.yaml
- pipeline.png
- predict.py
- pyproject.toml
- README.md
// repository documentation
Was this content helpful?
(0 ratings)