Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- weizechen/RL-Compositionality-Stage1-RFT-Data
|
| 4 |
+
base_model:
|
| 5 |
+
- meta-llama/Llama-3.1-8B-Instruct
|
| 6 |
+
---
|
| 7 |
+
The model after Stage 1 RFT.
|
| 8 |
+
|
| 9 |
+
Paper: https://huggingface.co/papers/2509.25123
|
| 10 |
+
|
| 11 |
+
Code: https://github.com/PRIME-RL/RL-Compositionality
|