TeeZee
/

Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

TeeZee commited on Apr 11

Commit

1834a84

•

1 Parent(s): 2e195b5

Update README.md

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -11,4 +11,7 @@ Precise recipe used by Upstage to create [SOLAR](https://huggingface.co/upstage/
 - seems that this model scores highest amongst all versions of original Bielik models, further finetunig should improve results even more.
   ![imgage/png](https://huggingface.co/TeeZee/Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1/resolve/main/OpenLLMLeaderboard_results.png)

 - seems that this model scores highest amongst all versions of original Bielik models, further finetunig should improve results even more.
   ![imgage/png](https://huggingface.co/TeeZee/Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1/resolve/main/OpenLLMLeaderboard_results.png)
+- on dedicated to Polish speaking LLM leaderboards, its 2nd, just behind instruct version used for this merge, and thats to be expected when applying DUS merge - very small qulity loss.
+[Polish LLMs leaderboards](https://huggingface.co/spaces/speakleash/open_pl_llm_leaderboard)