jpacifico
/

Chocolatine-14B-Instruct-DPO-v1.2

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

jpacifico commited on Aug 22, 2024

Commit

92bbdc4

•

1 Parent(s): 2e7e425

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -19,9 +19,9 @@ using the [jpacifico/french-orca-dpo-pairs-revised](https://huggingface.co/datas
 Training in French also improves the model in English, surpassing the performances of its base model.
 Window context = 4k tokens
-**Note: Version 1.2 is an improvement in French compared to the previous version.
-For English usage, however, [version 1.1](https://huggingface.co/jpacifico/Chocolatine-14B-Instruct-DPO-v1.1) is recommended as it is more robust in English.**
 ### MT-Bench-French

 Training in French also improves the model in English, surpassing the performances of its base model.
 Window context = 4k tokens
+### OpenLLM Leaderboard
+TBD
 ### MT-Bench-French