Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
- GRPO
|
| 13 |
- RL
|
| 14 |
---
|
| 15 |
-
|
| 16 |
This is a reproduction of DeepSeek R1 for text-to-graph information extraction tasks. It's based on the Qwen-2.5-0.5B model and was trained using both reinforcement learning (GRPO) and supervised learning.
|
| 17 |
|
| 18 |
### How to use:
|
|
|
|
| 12 |
- GRPO
|
| 13 |
- RL
|
| 14 |
---
|
| 15 |
+
### Text2Graph-R1-Qwen2.5-0.5b
|
| 16 |
This is a reproduction of DeepSeek R1 for text-to-graph information extraction tasks. It's based on the Qwen-2.5-0.5B model and was trained using both reinforcement learning (GRPO) and supervised learning.
|
| 17 |
|
| 18 |
### How to use:
|