Update README.md
Browse files
README.md
CHANGED
|
@@ -11,14 +11,6 @@ library_name: transformers
|
|
| 11 |
JET-7B is designed to improve the efficient reasoning of LLMs by training the base **DeepSeek-Distill-Qwen-7B** model with a reinforcement learning framework. Through this training, the model learns to generate high-quality reasoning steps while minimizing unnecessary computation and token usage.
|
| 12 |
|
| 13 |
|
| 14 |
-
# Training Code
|
| 15 |
-
|
| 16 |
-
Our training pipeline is available on GitHub: [Just-Enough-Think](https://github.com/JinyiHan99/Just-Enough-Think/)
|
| 17 |
-
|
| 18 |
-
The repository contains scripts for:
|
| 19 |
-
- RL-based fine-tuning
|
| 20 |
-
- Evaluation and benchmarking
|
| 21 |
-
|
| 22 |
## Chat Template
|
| 23 |
|
| 24 |
```python
|
|
|
|
| 11 |
JET-7B is designed to improve the efficient reasoning of LLMs by training the base **DeepSeek-Distill-Qwen-7B** model with a reinforcement learning framework. Through this training, the model learns to generate high-quality reasoning steps while minimizing unnecessary computation and token usage.
|
| 12 |
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
## Chat Template
|
| 15 |
|
| 16 |
```python
|