Instructions to use ArinUmut/pan-turkic-tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ArinUmut/pan-turkic-tokenizer with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ArinUmut/pan-turkic-tokenizer", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add tokenizer_config.json
Browse files- tokenizer_config.json +9 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 3 |
+
"add_bos_token": false,
|
| 4 |
+
"add_eos_token": false,
|
| 5 |
+
"bos_token": "<bos>",
|
| 6 |
+
"eos_token": "<eos>",
|
| 7 |
+
"unk_token": "<unk>",
|
| 8 |
+
"pad_token": "<pad>"
|
| 9 |
+
}
|