Hugging Face's logo

OpenRLHF
/
Llama-3-8b-sft-mixture

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
chuyi777 commited on
Commit
03334dc
·
verified ·
1 Parent(s): ffb8888

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -3,11 +3,12 @@ library_name: transformers
3
  tags: []
4
  ---
5
 
 
 
 
 
6
  This is the SFT checkpoint used for the project [Online-RLHF](https://github.com/RLHFlow/Online-RLHF). Also, check the [technical report here](https://arxiv.org/pdf/2405.07863).
7
 
8
  The model is trained from [meta-llama/Meta-Llama-3-8B](https://huggingface.co/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.
9
 
10
- The datasets included: ShareGPT, Evol-Instruct, SlimOrca, MathInstruct, Magicoder-Evol-Instruct, GPT4-LLM, OrcaMath, GPTeacher, UltraInteract
11
-
12
-
13
- OpenLLMAI fixed the `generation_config.json`.
 
3
  tags: []
4
  ---
5
 
6
+ >Copy from https://huggingface.co/RLHFlow/LLaMA3-SFT
7
+ >
8
+ >We fixed the `generation_config.json`.
9
+
10
  This is the SFT checkpoint used for the project [Online-RLHF](https://github.com/RLHFlow/Online-RLHF). Also, check the [technical report here](https://arxiv.org/pdf/2405.07863).
11
 
12
  The model is trained from [meta-llama/Meta-Llama-3-8B](https://huggingface.co/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.
13
 
14
+ The datasets included: ShareGPT, Evol-Instruct, SlimOrca, MathInstruct, Magicoder-Evol-Instruct, GPT4-LLM, OrcaMath, GPTeacher, UltraInteract.