Downloads · 30 days
364
0% of all-time downloads
Llama-3-8b-sft-mixture
OpenRLHF/Llama-3-8b-sft-mixture
Llama-3-8b-sft-mixture is a text generation model from OpenRLHF. Use it when you need the model to write or continue text. It is set up for transformers.
Copy from https://huggingface.co/RLHFlow/LLaMA3-SFT We fixed the generationconfig.json.
All-time downloads
185K
Public
Parameters
8B
16.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Jun 14, 2024
- Updated
- Jun 14, 2024
- SHA
- 03334dc4
Try a prompt
Model card
From the Hugging Face model README
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.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Featherless Ai
- live
- Created
- Jun 14, 2024
- Updated
- Jun 14, 2024