Commit
·
f47cf05
1
Parent(s):
6672f2c
Update README.md
Browse files
README.md
CHANGED
|
@@ -47,7 +47,7 @@ We jointly optimize the model on the conventional language modeling objective an
|
|
| 47 |
|
| 48 |
We evaluate the model on the datasets of [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). The results are shown below:
|
| 49 |
|
| 50 |
-
| Metric | ReLU Value | Orig Value |
|
| 51 |
|-----------------------|-------|------------|
|
| 52 |
| ARC (25-shot) | 49.48 | 53.07 |
|
| 53 |
| HellaSwag (10-shot) | 74.67 | 78.59 |
|
|
|
|
| 47 |
|
| 48 |
We evaluate the model on the datasets of [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). The results are shown below:
|
| 49 |
|
| 50 |
+
| Metric | ReLU Value | [Orig Value](https://huggingface.co/datasets/open-llm-leaderboard/details_meta-llama__Llama-2-7b-hf) |
|
| 51 |
|-----------------------|-------|------------|
|
| 52 |
| ARC (25-shot) | 49.48 | 53.07 |
|
| 53 |
| HellaSwag (10-shot) | 74.67 | 78.59 |
|