cloudyu
/

Mixtral-8x7B-Instruct-v0.1-DPO

Text Generation

Mixture of Experts

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

cloudyu commited on Jan 23

Commit

437230c

•

1 Parent(s): 74d460b

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -17,6 +17,6 @@ tags:
  * [DPO Trainer](https://huggingface.co/docs/trl/main/en/dpo_trainer)
-Metrics improved by DPO traingin after 100 steps
 ![Metrsc improment](mixtral-dpo.jpg)

  * [DPO Trainer](https://huggingface.co/docs/trl/main/en/dpo_trainer)
+Metrics improved by Truthful DPO traingin after 100 steps
 ![Metrsc improment](mixtral-dpo.jpg)