Technoculture
/

Medorca-2x7b

Text Generation

Mixture of Experts

epfl-llm/meditron-7b

microsoft/Orca-2-7b

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

satyamt commited on Jan 16

Commit

bb2b27d

•

1 Parent(s): 597c5b2

Update README.md

Files changed (1) hide show

README.md +15 -14

README.md CHANGED Viewed

@@ -15,20 +15,21 @@ Medorca-11B is a Mixure of Experts (MoE) made with the following models:
 ## Evaluations
-| Benchmark | Medorca-11B | meditron-7b | Orca-2-7b | meditron-70b |
-| --- | --- | --- | --- | --- |
-| MedMCQA |  |  |  |  |
-| ClosedPubMedQA |  |  |  |  |
-| PubMedQA |  |  |  |  |
-| MedQA |  |  |  |  |
-| MedQA4 |  |  |  |  |
-| MedicationQA |  |  |  |  |
-| MMLU Medical |  |  |  |  |
-| TruthfulQA |  |  |  |  |
-| GSM8K |  |  |  |  |
-| ARC |  |  |  |  |
-| HellaSwag |  |  |  |  |
-| Winogrande |  |  |  |  |
 ## 🧩 Configuration

 ## Evaluations
+| Benchmark | Medorca-2x7b | Orca-2-7b | llama-2-7b | meditron-7b | meditron-70b |
+| --- | --- | --- | --- | --- | --- |
+| MedMCQA |  |  |  |  |  |
+| ClosedPubMedQA |  |  |  |  |  |
+| PubMedQA |  |  |  |  |  |
+| MedQA |  |  |  |  |  |
+| MedQA4 |  |  |  |  |  |
+| MedicationQA |  |  |  |  |  |
+| MMLU Medical |  |  |  |  |  |
+| MMLU | 53.3 | 56.37 |  |  |  |
+| TruthfulQA | 48.04 | 52.45 |  |  |  |
+| GSM8K | 20.64 | 14.71 |  |  |  |
+| ARC | 54.1 | 54.1 |  |  |  |
+| HellaSwag | 76.04 | 76.19 |  |  |  |
+| Winogrande | 74.51 | 73.48 |  |  |  |
 ## 🧩 Configuration