Adding Evaluation Results
#1
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -9,4 +9,17 @@ The training data, sourced from HuggingFaceH4/no_robots, ensures that Barcenas 3
|
|
| 9 |
|
| 10 |
Whether used for creative writing, content generation, or other text-based tasks, Barcenas 3b stands out as a reliable and innovative AI model. Its proficiency in understanding and generating contextually appropriate text sets it apart in the realm of natural language processing, offering users a powerful tool for enhancing their applications and workflows.
|
| 11 |
|
| 12 |
-
Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
Whether used for creative writing, content generation, or other text-based tasks, Barcenas 3b stands out as a reliable and innovative AI model. Its proficiency in understanding and generating contextually appropriate text sets it apart in the realm of natural language processing, offering users a powerful tool for enhancing their applications and workflows.
|
| 11 |
|
| 12 |
+
Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽
|
| 13 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 14 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Danielbrdz__Barcenas-3b)
|
| 15 |
+
|
| 16 |
+
| Metric | Value |
|
| 17 |
+
|-----------------------|---------------------------|
|
| 18 |
+
| Avg. | 36.45 |
|
| 19 |
+
| ARC (25-shot) | 43.17 |
|
| 20 |
+
| HellaSwag (10-shot) | 67.82 |
|
| 21 |
+
| MMLU (5-shot) | 29.16 |
|
| 22 |
+
| TruthfulQA (0-shot) | 41.56 |
|
| 23 |
+
| Winogrande (5-shot) | 66.22 |
|
| 24 |
+
| GSM8K (5-shot) | 2.5 |
|
| 25 |
+
| DROP (3-shot) | 4.69 |
|