Update README.md
Browse files
README.md
CHANGED
|
@@ -40,6 +40,11 @@ library_name: transformers
|
|
| 40 |
|
| 41 |
We have a free Google Colab notebook for turning Phi-4 into a reasoning model: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4_(14B)-GRPO.ipynb
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
## ✨ Finetune for Free
|
| 45 |
|
|
|
|
| 40 |
|
| 41 |
We have a free Google Colab notebook for turning Phi-4 into a reasoning model: https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4_(14B)-GRPO.ipynb
|
| 42 |
|
| 43 |
+
### Unsloth bug fixes:
|
| 44 |
+
1. Padding and EOS tokens are the same - fixed this.
|
| 45 |
+
2. Chat template had extra EOS token - removed this. Otherwise you will be <|end|> during inference.
|
| 46 |
+
3. EOS token should be <|end|> not <|endoftext|>. Otherwise it'll terminate at <|endoftext|>
|
| 47 |
+
4. Changed unk_token to � from EOS.
|
| 48 |
|
| 49 |
## ✨ Finetune for Free
|
| 50 |
|