Update README.md
Browse files
README.md
CHANGED
|
@@ -5,11 +5,11 @@ language:
|
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
tags:
|
| 7 |
- deepscaler
|
| 8 |
-
- reasoning
|
| 9 |
- grpo
|
| 10 |
- qwen2
|
| 11 |
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
| 12 |
license: other
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
# DECS_1.5B
|
|
@@ -21,6 +21,9 @@ DECS_1.5B is a reasoning-focused causal language model built from `deepseek-ai/D
|
|
| 21 |
- Base model: `deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B`
|
| 22 |
- Upload date: `2026-02-24`
|
| 23 |
- Recommended use: long-form reasoning and mathematical/problem-solving style generation
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
## Quick Start (Transformers)
|
| 26 |
|
|
@@ -86,4 +89,4 @@ booktitle={The Fourteenth International Conference on Learning Representations},
|
|
| 86 |
year={2026},
|
| 87 |
url={https://openreview.net/forum?id=kdeiRledV6}
|
| 88 |
}
|
| 89 |
-
```
|
|
|
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
tags:
|
| 7 |
- deepscaler
|
|
|
|
| 8 |
- grpo
|
| 9 |
- qwen2
|
| 10 |
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
| 11 |
license: other
|
| 12 |
+
library_name: transformers
|
| 13 |
---
|
| 14 |
|
| 15 |
# DECS_1.5B
|
|
|
|
| 21 |
- Base model: `deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B`
|
| 22 |
- Upload date: `2026-02-24`
|
| 23 |
- Recommended use: long-form reasoning and mathematical/problem-solving style generation
|
| 24 |
+
- Paper link: https://arxiv.org/pdf/2509.25827
|
| 25 |
+
- Project page: https://pixas.github.io/decs-iclr26-site/
|
| 26 |
+
- Github repo: https://github.com/pixas/DECS
|
| 27 |
|
| 28 |
## Quick Start (Transformers)
|
| 29 |
|
|
|
|
| 89 |
year={2026},
|
| 90 |
url={https://openreview.net/forum?id=kdeiRledV6}
|
| 91 |
}
|
| 92 |
+
```
|