Upd link to training recipie
#12
by
bzz2
- opened
README.md
CHANGED
|
@@ -95,7 +95,7 @@ We train the models using the [alignment-handbook](https://github.com/huggingfac
|
|
| 95 |
- warmup ratio 0.1
|
| 96 |
- global batch size 262k tokens
|
| 97 |
|
| 98 |
-
You can find the training recipe here: https://github.com/huggingface/alignment-handbook/tree/
|
| 99 |
|
| 100 |
# Citation
|
| 101 |
```bash
|
|
|
|
| 95 |
- warmup ratio 0.1
|
| 96 |
- global batch size 262k tokens
|
| 97 |
|
| 98 |
+
You can find the training recipe here: https://github.com/huggingface/alignment-handbook/tree/main/recipes/smollm
|
| 99 |
|
| 100 |
# Citation
|
| 101 |
```bash
|