Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- ig
|
| 6 |
+
- ja
|
| 7 |
+
- ar
|
| 8 |
+
tags:
|
| 9 |
+
- Tokenizers
|
| 10 |
+
- BPE
|
| 11 |
+
---
|
| 12 |
+
## NeonTech Tokenizers
|
| 13 |
+
|
| 14 |
+
Custom multimodal tokenizer family for the NeonTech model series.
|
| 15 |
+
|
| 16 |
+
## Available Versions
|
| 17 |
+
|
| 18 |
+
- v1 — 131,072 vocab, DeepSeek V4 base + Igbo/Japanese/Arabic extensions, 80 special tokens
|
| 19 |
+
- See the v1 branch for full details on special tokens and architecture.
|
| 20 |
+
|
| 21 |
+
## Usage
|
| 22 |
+
|
| 23 |
+
```python
|
| 24 |
+
from transformers import AutoTokenizer
|
| 25 |
+
tokenizer = AutoTokenizer.from_pretrained(“Neon-tech/Tokenizers”, revision=“v1”)
|
| 26 |
+
```
|