Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,14 @@
|
|
| 1 |
-
---
|
| 2 |
-
datasets:
|
| 3 |
-
- PatrickHaller/dsir-pile-100M-words
|
| 4 |
-
|
|
|
|
|
|
|
| 5 |
|
| 6 |
-
Our model for the 2024 BabyLM challenge 100M words track.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- PatrickHaller/dsir-pile-100M-words
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
---
|
| 7 |
|
| 8 |
+
Our model for the 2024 BabyLM challenge 100M words track.
|
| 9 |
+
|
| 10 |
+
To download and use this model the [fla](https://github.com/sustcsonglin/flash-linear-attention) package has to be installed:
|
| 11 |
+
|
| 12 |
+
```bash
|
| 13 |
+
pip install -U git+https://github.com/sustcsonglin/flash-linear-attention
|
| 14 |
+
```
|