Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ language:
|
|
| 3 |
- en
|
| 4 |
---
|
| 5 |
|
| 6 |
-
V1 of an English/code tokenizer. Equal mix between:
|
| 7 |
On the NL side:
|
| 8 |
- Books
|
| 9 |
- C4
|
|
|
|
| 3 |
- en
|
| 4 |
---
|
| 5 |
|
| 6 |
+
V1 of an English/code tokenizer. Byte-level BPE, 64k vocab. Equal mix between:
|
| 7 |
On the NL side:
|
| 8 |
- Books
|
| 9 |
- C4
|