Improve model card: Add architecture tags and GitHub link
Browse filesThis PR enhances the model card by:
- Adding `rwkv` and `qwen2.5` to the model's tags, improving discoverability for users looking for models related to these architectures.
- Including a direct link to the GitHub repository (`https://github.com/recursal/RADLADS`) in the main content, making it easier for users to access the project's source code and development details.
README.md
CHANGED
@@ -1,13 +1,17 @@
|
|
1 |
---
|
2 |
-
pipeline_tag: text-generation
|
3 |
library_name: transformers
|
4 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
5 |
---
|
6 |
|
7 |
# RADLADS
|
8 |
## Rapid Attention Distillation to Linear Attention Decoders at Scale
|
9 |
|
10 |
Paper link: https://arxiv.org/abs/2505.03005
|
|
|
11 |
|
12 |
Checkpoints: https://huggingface.co/collections/recursal/radlads-6818ee69e99e729ba8a87102
|
13 |
|
|
|
1 |
---
|
|
|
2 |
library_name: transformers
|
3 |
license: apache-2.0
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- rwkv
|
7 |
+
- qwen2.5
|
8 |
---
|
9 |
|
10 |
# RADLADS
|
11 |
## Rapid Attention Distillation to Linear Attention Decoders at Scale
|
12 |
|
13 |
Paper link: https://arxiv.org/abs/2505.03005
|
14 |
+
Code: https://github.com/recursal/RADLADS
|
15 |
|
16 |
Checkpoints: https://huggingface.co/collections/recursal/radlads-6818ee69e99e729ba8a87102
|
17 |
|