OmniAlign-V
Official Repository of ACL 2025 paper OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
File Explorer
Download Latest Version (.zip)- devcontainer.env
- devcontainer.json
- Dockerfile
- postCreateCommand.sh
- 1-usage.yaml
- 2-feature-request.yaml
- 3-question.yaml
- 4-discussion.yaml
- certificate.pem
- launch.json
- Customize_Component.md
- Data.md
- Evaluation.md
- Finetune_Custom_Data.md
- Intel.md
- LLaVA_Bench.md
- LLaVA_from_LLaMA2.md
- LoRA.md
- macOS.md
- MODEL_ZOO.md
- ScienceQA.md
- Windows.md
- benchmark_result.png
- dataset_performance.png
- framework.png
- statistic2.png
- teaser.png
- test_sqa_llava_13b_v0.json
- test_sqa_llava_lcs_558k_sqa_12e_vicuna_v1_3_13b.json
- 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
- 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
- configuration_internlm2.py
- modeling_internlm2.py
- tokenization_internlm2.py
- tokenization_internlm2_fast.py
- llava_internlm2.py
- llava_llama.py
- llava_mistral.py
- llava_mpt.py
- llava_qwen2.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
- sglang_worker.py
- test_message.py
- dataset.py
- llama_flash_attn_monkey_patch.py
- llama_xformers_attn_monkey_patch.py
- llava_trainer.py
- preprocess.py
- train.py
- train_dpo.py
- train_get_lastbatch.py
- train_mem.py
- train_xformers.py
- llava_internlm.py
- llava_qwen.py
- __init__.py
- constants.py
- conversation.py
- mm_utils.py
- utils.py
- ominialign_v_dpo.json
- omnialign_v.json
- OmniAlign-V_ACL_Poster.pptx
- dpo_anyres.sh
- sft_llavanext.sh
- sft_AR4_llavanext.sh
- sft_AR4_llavanext.sh
- pretrain.sh
- merge_lora_weights.py
- pretrain.sh
- upload_pypi.sh
- zero2.json
- zero3.json
- zero3_offload.json
- __init__.py
- base_environment.py
- __init__.py
- best_of_n_sampler.py
- dataset_formatting.py
- __init__.py
- base.py
- ddpo_config.py
- ddpo_trainer.py
- dpo_trainer.py
- iterative_sft_trainer.py
- model_config.py
- ppo_config.py
- ppo_trainer.py
- reward_config.py
- reward_trainer.py
- sft_trainer.py
- utils.py
- __init__.py
- core.py
- import_utils.py
- .dockerignore
- .editorconfig
- .gitattributes
- .gitignore
- cog.yaml
- eval_run.py
- LICENSE
- predict.py
- pyproject.toml
- README.md
- requirements.txt
# Installation Guide
1. Get the code
git clone https://github.com/PhoenixZ810/OmniAlign-V
Downloads the entire project code from GitHub to your computer.
cd OmniAlign-V
Moves into the project folder you just downloaded.
2. Python
Easy RecommendedPrerequisites
pip install -e '.[all]'
Installs the Python libraries listed in requirements.txt (or similar).
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)
