lgaalves
/

gpt2-xl_lima

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

lgaalves commited on Nov 15, 2023

Commit

6ddbebe

•

1 Parent(s): f7db5b1

Update README.md

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -18,11 +18,11 @@ pipeline_tag: text-generation
 | Metric                |gpt2-xl_lima |gpt2-xl (base) |
 |-----------------------|-------|-------|
-| Avg.                  | - |  36.66  |
-| ARC (25-shot)         | - |  30.29  |
-| HellaSwag (10-shot)   | - |  51.38  |
-| MMLU (5-shot)         | - |  26.43 |
-| TruthfulQA (0-shot)   | - |  38.54 |
 We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.

 | Metric                |gpt2-xl_lima |gpt2-xl (base) |
 |-----------------------|-------|-------|
+| Avg.                  | 36.65 |  **36.66**  |
+| ARC (25-shot)         | **31.14** |  30.29  |
+| HellaSwag (10-shot)   | 51.28 |  **51.38**  |
+| MMLU (5-shot)         | 25.43 |  **26.43** |
+| TruthfulQA (0-shot)   | **38.74** |  38.54 |
 We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.