Instructions to use mlx-community/Nemotron-Mini-4B-Instruct-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Nemotron-Mini-4B-Instruct-4bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Nemotron-Mini-4B-Instruct-4bit-mlx mlx-community/Nemotron-Mini-4B-Instruct-4bit-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +14 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"local_files_only": false,
|
| 8 |
+
"model_input_names": [
|
| 9 |
+
"input_ids",
|
| 10 |
+
"attention_mask"
|
| 11 |
+
],
|
| 12 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 13 |
+
"tokenizer_class": "TokenizersBackend"
|
| 14 |
+
}
|