empirischtech
/

Llama-3.1-10B-Instruct

Text Generation

Model card Files Files and versions Community

rwmasood commited on Mar 17

Commit

5b9c86f

·

verified ·

1 Parent(s): 8c72eb8

Update README.md

Files changed (1) hide show

README.md +7 -4

README.md CHANGED Viewed

@@ -115,10 +115,13 @@ The library used is [lm-evaluation-harness repository](https://github.com/Eleuth
 #### Main Results
-| Model |  ARC | HellaSwag | MMLU-Pro | IFEval |
-|------------------------|----------|--------|------|--------|
-| **Llama-3.1-8B-Instruct** | **55.05** | **79.28** | **40.34** | **59.95** |
-| **Llama-3.1-10B-Instruct** | **52.47** | **77.08** | **33.59** | **54.8** |
 #### Scripts to generate evalution results

 #### Main Results
+| Benchmark   |   **Llama-3.1-8B-Instruct**   |   **Llama-3.1-10B-Instruct**   |
+|------------|:------------------------:|:------------------------:|
+| ARC        |           55.05           |           52.47           |
+| HellaSwag  |           79.28           |           77.08           |
+| MMLU-Pro   |           40.34           |           33.59           |
+| IFEval     |           59.95           |           54.80           |
+| average | 58.66 | 54.49 |
 #### Scripts to generate evalution results