Commit ·
2fd0dff
1
Parent(s): 72a255a
Adding Evaluation Results
Browse filesThis is an automated PR created with https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr
The purpose of this PR is to add evaluation results from the Open LLM Leaderboard to your model card.
If you encounter any issues, please report them to https://huggingface.co/spaces/Weyaxi/open-llm-leaderboard-results-pr/discussions
README.md
CHANGED
|
@@ -50,4 +50,17 @@ print(tokenizer.decode(outputs[0],skip_special_tokens=True,clean_up_tokenization
|
|
| 50 |
|
| 51 |
The model achieves a 63.1% pass@1 on HumanEval and a 45.2% pass@1 on MBPP, however it is evident that these benchmarks are not representative of real-world usage of code models so we are launching the [Code Models Arena](https://arena.glaive.ai/) to let users vote on model outputs so we can have a better understanding of user preference on code models and come up with new and better benchmarks. We plan to release the Arena results as soon as we have a sufficient amount of data.
|
| 52 |
|
| 53 |
-
Join the Glaive [discord](https://discord.gg/fjQ4uf3yWD) for improvement suggestions, bug-reports and collaborating on more open-source projects.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
The model achieves a 63.1% pass@1 on HumanEval and a 45.2% pass@1 on MBPP, however it is evident that these benchmarks are not representative of real-world usage of code models so we are launching the [Code Models Arena](https://arena.glaive.ai/) to let users vote on model outputs so we can have a better understanding of user preference on code models and come up with new and better benchmarks. We plan to release the Arena results as soon as we have a sufficient amount of data.
|
| 52 |
|
| 53 |
+
Join the Glaive [discord](https://discord.gg/fjQ4uf3yWD) for improvement suggestions, bug-reports and collaborating on more open-source projects.
|
| 54 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 55 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_glaiveai__glaive-coder-7b)
|
| 56 |
+
|
| 57 |
+
| Metric | Value |
|
| 58 |
+
|-----------------------|---------------------------|
|
| 59 |
+
| Avg. | 36.42 |
|
| 60 |
+
| ARC (25-shot) | 42.66 |
|
| 61 |
+
| HellaSwag (10-shot) | 64.69 |
|
| 62 |
+
| MMLU (5-shot) | 37.15 |
|
| 63 |
+
| TruthfulQA (0-shot) | 39.88 |
|
| 64 |
+
| Winogrande (5-shot) | 59.75 |
|
| 65 |
+
| GSM8K (5-shot) | 5.23 |
|
| 66 |
+
| DROP (3-shot) | 5.55 |
|