Update README.md
Browse files
README.md
CHANGED
|
@@ -20,9 +20,7 @@ license: apache-2.0
|
|
| 20 |
|
| 21 |
|
| 22 |
We are excited to introduce JT-Math-8B-Instruct, a powerful 8-billion parameter model specialized for mathematical reasoning. It achieves state-of-the-art performance on major math benchmarks among models of its size.
|
| 23 |
-
|
| 24 |
JT-Math-8B-Instruct is fine-tuned from Jiutian-Math-8B-Base and has been optimized through a comprehensive process involving Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to enhance its mathematical problem-solving abilities and instruction-following capabilities.
|
| 25 |
-
|
| 26 |
For full transparency and reproducibility, please refer to our technical report which details our training recipe and pipeline.
|
| 27 |
|
| 28 |
|
|
|
|
| 20 |
|
| 21 |
|
| 22 |
We are excited to introduce JT-Math-8B-Instruct, a powerful 8-billion parameter model specialized for mathematical reasoning. It achieves state-of-the-art performance on major math benchmarks among models of its size.
|
|
|
|
| 23 |
JT-Math-8B-Instruct is fine-tuned from Jiutian-Math-8B-Base and has been optimized through a comprehensive process involving Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to enhance its mathematical problem-solving abilities and instruction-following capabilities.
|
|
|
|
| 24 |
For full transparency and reproducibility, please refer to our technical report which details our training recipe and pipeline.
|
| 25 |
|
| 26 |
|