Adding Evaluation Results
#10
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -209,4 +209,17 @@ See attached [Colab Notebook](https://huggingface.co/dfurman/Falcon-40B-Chat-v0.
|
|
| 209 |
- `peft`: 0.4.0.dev0
|
| 210 |
- `accelerate`: 0.19.0
|
| 211 |
- `bitsandbytes`: 0.39.0
|
| 212 |
-
- `einops`: 0.6.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 209 |
- `peft`: 0.4.0.dev0
|
| 210 |
- `accelerate`: 0.19.0
|
| 211 |
- `bitsandbytes`: 0.39.0
|
| 212 |
+
- `einops`: 0.6.1
|
| 213 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 214 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dfurman__falcon-40b-openassistant-peft)
|
| 215 |
+
|
| 216 |
+
| Metric | Value |
|
| 217 |
+
|-----------------------|---------------------------|
|
| 218 |
+
| Avg. | 51.17 |
|
| 219 |
+
| ARC (25-shot) | 62.63 |
|
| 220 |
+
| HellaSwag (10-shot) | 85.59 |
|
| 221 |
+
| MMLU (5-shot) | 57.77 |
|
| 222 |
+
| TruthfulQA (0-shot) | 51.02 |
|
| 223 |
+
| Winogrande (5-shot) | 81.45 |
|
| 224 |
+
| GSM8K (5-shot) | 13.34 |
|
| 225 |
+
| DROP (3-shot) | 6.36 |
|