Adding Evaluation Results
#8
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -45,3 +45,17 @@ Stable revision:
|
|
45 |
from transformers import AutoTokenizer
|
46 |
model = AutoModelForCausalLM.from_pretrained("w601sxs/b1ade-1b", torch_dtype=torch.bfloat16, device_map="auto", revision='b4b0fd71589e6590089e1ec14a840ecab10894ae')
|
47 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
from transformers import AutoTokenizer
|
46 |
model = AutoModelForCausalLM.from_pretrained("w601sxs/b1ade-1b", torch_dtype=torch.bfloat16, device_map="auto", revision='b4b0fd71589e6590089e1ec14a840ecab10894ae')
|
47 |
```
|
48 |
+
|
49 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
50 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_w601sxs__b1ade-1b)
|
51 |
+
|
52 |
+
| Metric | Value |
|
53 |
+
|-----------------------|---------------------------|
|
54 |
+
| Avg. | 28.54 |
|
55 |
+
| ARC (25-shot) | 28.58 |
|
56 |
+
| HellaSwag (10-shot) | 46.08 |
|
57 |
+
| MMLU (5-shot) | 25.11 |
|
58 |
+
| TruthfulQA (0-shot) | 41.34 |
|
59 |
+
| Winogrande (5-shot) | 53.83 |
|
60 |
+
| GSM8K (5-shot) | 0.61 |
|
61 |
+
| DROP (3-shot) | 4.25 |
|