Add pipeline tag, library name and link to paper (#1)
Browse files- Add pipeline tag, library name and link to paper (cb2fac47843e3ed3d3ff331d3b0b1e0f37946267)
Co-authored-by: Niels Rogge <[email protected]>
README.md
CHANGED
@@ -1,10 +1,15 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
base_model:
|
4 |
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
|
|
|
|
|
|
5 |
---
|
|
|
6 |
# Light-R1-32B-DS: near-SOTA 32B Math Model with Only 3K Data
|
7 |
|
|
|
|
|
8 |
|Model|Trained From|Release Date|AIME24|AIME25|GPQA|
|
9 |
| ---- | ---- | ---- | ---- | ---- | ---- |
|
10 |
|DeepSeek-R1-Distill-Qwen-32B|Qwen2.5-32B|25.1.20|72.6|54.9|62.1|
|
|
|
1 |
---
|
|
|
2 |
base_model:
|
3 |
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
4 |
+
license: apache-2.0
|
5 |
+
library_name: transformers
|
6 |
+
pipeline_tag: text-generation
|
7 |
---
|
8 |
+
|
9 |
# Light-R1-32B-DS: near-SOTA 32B Math Model with Only 3K Data
|
10 |
|
11 |
+
Paper: https://huggingface.co/papers/2503.10460
|
12 |
+
|
13 |
|Model|Trained From|Release Date|AIME24|AIME25|GPQA|
|
14 |
| ---- | ---- | ---- | ---- | ---- | ---- |
|
15 |
|DeepSeek-R1-Distill-Qwen-32B|Qwen2.5-32B|25.1.20|72.6|54.9|62.1|
|