RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness
Paper β’ 2405.17220 β’ Published β’ 1
How to use openbmb/RLHF-V-SFT with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="openbmb/RLHF-V-SFT") # Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("openbmb/RLHF-V-SFT", dtype="auto")How to use openbmb/RLHF-V-SFT with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openbmb/RLHF-V-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "openbmb/RLHF-V-SFT",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/openbmb/RLHF-V-SFT
How to use openbmb/RLHF-V-SFT with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "openbmb/RLHF-V-SFT" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "openbmb/RLHF-V-SFT",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "openbmb/RLHF-V-SFT" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "openbmb/RLHF-V-SFT",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use openbmb/RLHF-V-SFT with Docker Model Runner:
docker model run hf.co/openbmb/RLHF-V-SFT
If you find this dataset helpful, please consider cite our papers π:
@article{yu2023rlhf,
title={Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback},
author={Yu, Tianyu and Yao, Yuan and Zhang, Haoye and He, Taiwen and Han, Yifeng and Cui, Ganqu and Hu, Jinyi and Liu, Zhiyuan and Zheng, Hai-Tao and Sun, Maosong and others},
journal={arXiv preprint arXiv:2312.00849},
year={2023}
}
@article{yu2024rlaifv,
title={RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness},
author={Yu, Tianyu and Zhang, Haoye and Yao, Yuan and Dang, Yunkai and Chen, Da and Lu, Xiaoman and Cui, Ganqu and He, Taiwen and Liu, Zhiyuan and Chua, Tat-Seng and Sun, Maosong},
journal={arXiv preprint arXiv:2405.17220},
year={2024},
}