Update README.md
Browse files
README.md
CHANGED
|
@@ -77,7 +77,7 @@ we introduce Fusion-T1, which incorporates cold-start data before RL.
|
|
| 77 |
To support the research community, we have open-sourced Fusion-T1-Zero, Fusion-T1, and six dense models distilled from Fusion-T1 based on Llama and Qwen. Fusion-T1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
|
| 78 |
|
| 79 |
<p align="center">
|
| 80 |
-
<img width="80%" src="
|
| 81 |
</p>
|
| 82 |
|
| 83 |
## 2. Model Summary
|
|
|
|
| 77 |
To support the research community, we have open-sourced Fusion-T1-Zero, Fusion-T1, and six dense models distilled from Fusion-T1 based on Llama and Qwen. Fusion-T1-Distill-Qwen-32B outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
|
| 78 |
|
| 79 |
<p align="center">
|
| 80 |
+
<img width="80%" src="https://i.ibb.co/Bw8N1VY/image.png">
|
| 81 |
</p>
|
| 82 |
|
| 83 |
## 2. Model Summary
|