Add pipeline tag and library name
#1
by
nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
The *TokenFormer* is a **fully attention-based architecture**
|
|
@@ -17,7 +19,7 @@ same data, in the exact same order.
|
|
| 17 |
- Developed by: [Haiyang Wang](https://haiyang-w.github.io/)
|
| 18 |
- Model type: TokenFormer-based Language Model
|
| 19 |
- Language: English
|
| 20 |
-
- Learn more: [TokenFormer's GitHub repository](https://github.com/Haiyang-W/TokenFormer)
|
| 21 |
for training procedure, config files, and details on how to use.
|
| 22 |
[See paper](https://arxiv.org/pdf/2410.23168) for more evals and implementation
|
| 23 |
details.
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
+
library_name: gpt-neox
|
| 5 |
---
|
| 6 |
|
| 7 |
The *TokenFormer* is a **fully attention-based architecture**
|
|
|
|
| 19 |
- Developed by: [Haiyang Wang](https://haiyang-w.github.io/)
|
| 20 |
- Model type: TokenFormer-based Language Model
|
| 21 |
- Language: English
|
| 22 |
+
- Learn more: [TokenFormer's GitHub repository](https://github.com/Haiyang-W/TokenFormer) and [project page](https://haiyang-w.github.io/tokenformer.github.io/)
|
| 23 |
for training procedure, config files, and details on how to use.
|
| 24 |
[See paper](https://arxiv.org/pdf/2410.23168) for more evals and implementation
|
| 25 |
details.
|