Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,11 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
license: mit
|
| 4 |
language:
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# Walker
|
|
@@ -130,4 +131,4 @@ $$
|
|
| 130 |
|
| 131 |
**Walker:** *How is the representation moving?*
|
| 132 |
|
| 133 |
-
> **Walker is a Transformer that not only looks at the sequence, but also walks through the trajectory of its own representations.**
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
license: mit
|
| 3 |
language:
|
| 4 |
+
- en
|
| 5 |
+
datasets:
|
| 6 |
+
- wikimedia/wikipedia
|
| 7 |
+
- bctnry/CosmopediaV2
|
| 8 |
+
- OctoThinker/MegaMath-Web-Pro-Max
|
| 9 |
---
|
| 10 |
|
| 11 |
# Walker
|
|
|
|
| 131 |
|
| 132 |
**Walker:** *How is the representation moving?*
|
| 133 |
|
| 134 |
+
> **Walker is a Transformer that not only looks at the sequence, but also walks through the trajectory of its own representations.**
|