doc: update README
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Multistral Tokenizer
|
| 2 |
|
| 3 |
Training completed successfully!
|
|
@@ -29,4 +42,4 @@ from multistral.multistraltokenizer import MultistralTokenizer
|
|
| 29 |
tokenizer = MultistralTokenizer.from_pretrained("models/aizia_tokenizer")
|
| 30 |
tokens = tokenizer.encode("Your text here")
|
| 31 |
text = tokenizer.decode(tokens)
|
| 32 |
-
```
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: isc
|
| 3 |
+
datasets:
|
| 4 |
+
- HuggingFaceFW/fineweb
|
| 5 |
+
- HuggingFaceFW/fineweb-2
|
| 6 |
+
language:
|
| 7 |
+
- fr
|
| 8 |
+
- en
|
| 9 |
+
- zh
|
| 10 |
+
pipeline_tag: token-classification
|
| 11 |
+
tags:
|
| 12 |
+
- code
|
| 13 |
+
---
|
| 14 |
# Multistral Tokenizer
|
| 15 |
|
| 16 |
Training completed successfully!
|
|
|
|
| 42 |
tokenizer = MultistralTokenizer.from_pretrained("models/aizia_tokenizer")
|
| 43 |
tokens = tokenizer.encode("Your text here")
|
| 44 |
text = tokenizer.decode(tokens)
|
| 45 |
+
```
|