Copy from https://huggingface.co/RLHFlow/LLaMA3-SFT
We fixed the
generation_config.json.
This is the SFT checkpoint used for the project Online-RLHF. Also, check the technical report here.
The model is trained from meta-llama/Meta-Llama-3-8B on a mixture of diverse open-source high-quality data for 1 epoch with detailed parameters in the report. It has not been trained by RLHF and can serve as a good starting point for the RLHF research.
The datasets included: ShareGPT, Evol-Instruct, SlimOrca, MathInstruct, Magicoder-Evol-Instruct, GPT4-LLM, OrcaMath, GPTeacher, UltraInteract.
- Downloads last month
- 14,000
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.