LumiOpen
/

Poro-34B-chat

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

laineyyy commited on May 27

Commit

c9757cd

•

1 Parent(s): 8b4fabc

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -54,10 +54,10 @@ We relied on the popular MTBench benchmark to evaluate multi-turn performance.
 Since MTBench is an English only benchmark, we also release this fork of [MTBench Finnish](https://github.com/LumiOpen/FastChat/tree/main/fastchat/llm_judge) with multilingual support and machine translated Finnish prompts.  Our scores for both benchmarks follow.
-| Eval | Score  |
-| :-------------- | :----: |
-| MTBench         | 5.93   |
-| MTBench Finnish | 5.90   |
 ## License

 Since MTBench is an English only benchmark, we also release this fork of [MTBench Finnish](https://github.com/LumiOpen/FastChat/tree/main/fastchat/llm_judge) with multilingual support and machine translated Finnish prompts.  Our scores for both benchmarks follow.
+| Eval            | Overall | Coding | Extraction | Humanities | Math  | Reasoning | Roleplay | STEM  | Writing |
+| :----           |  :---:  |  :---: |   :---:    | :---:      | :---: | :---:     | :---:    | :---: |   ----: |
+| MTBench English | 6.16    | 3.65   | 6.55       | 9.6        | 2.25  | 4.25      | 7.25     | 7.42  | 8.37    |
+| MTBench Finnish | 5.73    | 3.05   | 6.05       | 9.6        | 1.25  | 3.65      | 7.0      | 7.65  | 7.6     |
 ## License