mayacinka
/

ExpertRamonda-7Bx2_MoE

Text Generation

Mixture of Experts

mlabonne/AlphaMonarch-7B

bardsai/jaskier-7b-dpo-v5.6

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

mayacinka commited on Feb 25

Commit

4f01890

•

1 Parent(s): ec52bba

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -24,7 +24,8 @@ ExpertRamonda-7Bx2_MoE is a Mixure of Experts (MoE) made with the following mode
 ### Open LLM Leaderboard
 | Model                  | Average | ARC  | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
 |------------------------|--------:|-----:|----------:|-----:|-----------:|-----------:|------:|
-| mayacinka/ExpertRamonda-7Bx2_MoE |   / | 86.87 |      87.51| / |      61.63 |      / |  /|
 ### MMLU
 |      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|

 ### Open LLM Leaderboard
 | Model                  | Average | ARC  | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
 |------------------------|--------:|-----:|----------:|-----:|-----------:|-----------:|------:|
+| mayacinka/ExpertRamonda-7Bx2_MoE |   / | 86.87 |      87.51| / |      61.63 |      81.85 |  72.71|
 ### MMLU
 |      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|