Commit
•
788aa8f
1
Parent(s):
7347f2c
Update README.md (#2)
Browse files- Update README.md (9e9d49095058b7bd604356bd131a63e5c640929d)
Co-authored-by: Dhia hf <Dhia-GB@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -88,7 +88,10 @@ print(response)
|
|
| 88 |
<br>
|
| 89 |
|
| 90 |
## Benchmarks
|
| 91 |
-
We report in the following table our internal pipeline benchmarks
|
|
|
|
|
|
|
|
|
|
| 92 |
|
| 93 |
<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
|
| 94 |
<colgroup>
|
|
|
|
| 88 |
<br>
|
| 89 |
|
| 90 |
## Benchmarks
|
| 91 |
+
We report in the following table our internal pipeline benchmarks.
|
| 92 |
+
- We use [lm-evaluation harness](https://github.com/EleutherAI/lm-evaluation-harness).
|
| 93 |
+
- We report **raw scores** obtained by applying chat template **without fewshot_as_multiturn** (unlike Llama3.1).
|
| 94 |
+
- We use same batch-size across all models.
|
| 95 |
|
| 96 |
<table border="1" style="width: 100%; text-align: center; border-collapse: collapse;">
|
| 97 |
<colgroup>
|