Update README.md
Browse files
README.md
CHANGED
|
@@ -31,10 +31,6 @@ training.
|
|
| 31 |
3. 📈 Flexible scalability: Robust performance across diverse inference budgets on reasoning benchmarks like AIME and LiveCodeBench.
|
| 32 |
4. ⚙️ Better performance with fewer tokens: Our trained model generates outputs that are 30% shorter while maintaining (or even improving) accuracy.
|
| 33 |
|
| 34 |
-
<p align="center">
|
| 35 |
-
<img src="figs/aime.png" width="40%" /><img src="figs/livecode.png" width="40%" />
|
| 36 |
-
</p>
|
| 37 |
-
|
| 38 |
<p align="center">
|
| 39 |
<img src="figs/codetable.png" width="90%" />
|
| 40 |
</p>
|
|
|
|
| 31 |
3. 📈 Flexible scalability: Robust performance across diverse inference budgets on reasoning benchmarks like AIME and LiveCodeBench.
|
| 32 |
4. ⚙️ Better performance with fewer tokens: Our trained model generates outputs that are 30% shorter while maintaining (or even improving) accuracy.
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
<p align="center">
|
| 35 |
<img src="figs/codetable.png" width="90%" />
|
| 36 |
</p>
|