Update README.md
Browse files
README.md
CHANGED
|
@@ -64,6 +64,12 @@ All notebooks are **beginner friendly**! Add your dataset, click "Run All", and
|
|
| 64 |
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
|
| 65 |
|
| 66 |
## Model Summary
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
|
| 68 |
Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures.
|
| 69 |
|
|
|
|
| 64 |
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
|
| 65 |
|
| 66 |
## Model Summary
|
| 67 |
+
|
| 68 |
+
### Unsloth bug fixes:
|
| 69 |
+
1. Padding and EOS tokens are the same - fixed this
|
| 70 |
+
2. Chat template had extra EOS token - removed this
|
| 71 |
+
3. EOS token should be <|end|> not <|endoftext|>
|
| 72 |
+
4. Changed unk_token to �
|
| 73 |
|
| 74 |
Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures.
|
| 75 |
|