Hugging Face's logo

glorgao
/
SelectiveDPO-Mistral-7B-SFT-UFBinarized

Text Generation
Transformers
Safetensors
mistral
conversational
text-generation-inference
Model card Files Community
glorgao commited on
Commit
8077e6a
·
verified ·
1 Parent(s): a1e58b8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -5,7 +5,7 @@ datasets:
5
  base_model:
6
  - HuggingFaceH4/mistral-7b-sft-beta
7
  ---
8
- This model is fine-tuned from the HuggingFaceH4/mistral-7b-sft-beta model using the SelectiveDPO algorithm on the Ultrafeedback_binarized dataset.
9
 
10
  For the recipe to reproduce this model, please visit our [GitHub page](https://github.com/glorgao/SelectiveDPO).
11
 
 
5
  base_model:
6
  - HuggingFaceH4/mistral-7b-sft-beta
7
  ---
8
+ This model is fine-tuned from the HuggingFaceH4/mistral-7b-sft-beta model using [SelectiveDPO](https://huggingface.co/papers/2502.09650) on the Ultrafeedback_binarized dataset.
9
 
10
  For the recipe to reproduce this model, please visit our [GitHub page](https://github.com/glorgao/SelectiveDPO).
11