Update README.md
Browse files
README.md
CHANGED
|
@@ -44,4 +44,12 @@ datasets:
|
|
| 44 |
- lightblue/reasoning-multilingual-R1-Llama-70B-train
|
| 45 |
base_model:
|
| 46 |
- Qwen/Qwen2.5-1.5B-Instruct
|
| 47 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
- lightblue/reasoning-multilingual-R1-Llama-70B-train
|
| 45 |
base_model:
|
| 46 |
- Qwen/Qwen2.5-1.5B-Instruct
|
| 47 |
+
---
|
| 48 |
+
|
| 49 |
+
It's a distill model like s1 and deepseek-r1-distill.
|
| 50 |
+
|
| 51 |
+
It's test model. I hope I can reproduce a rl model like RL-Zero.
|
| 52 |
+
|
| 53 |
+
This model is a mini-step.
|
| 54 |
+
|
| 55 |
+
Thanks for evveryone in the open community.
|