Instructions to use mlx-community/dbrx-instruct-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/dbrx-instruct-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir dbrx-instruct-4bit mlx-community/dbrx-instruct-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
add chat_template
Browse filesI am guessing, it needs chat_template in order to handle chat properly
- tokenizer_config.json +1 -0
tokenizer_config.json
CHANGED
|
@@ -46,6 +46,7 @@
|
|
| 46 |
null
|
| 47 |
]
|
| 48 |
},
|
|
|
|
| 49 |
"bos_token": "<|endoftext|>",
|
| 50 |
"clean_up_tokenization_spaces": true,
|
| 51 |
"encoding_name": null,
|
|
|
|
| 46 |
null
|
| 47 |
]
|
| 48 |
},
|
| 49 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 50 |
"bos_token": "<|endoftext|>",
|
| 51 |
"clean_up_tokenization_spaces": true,
|
| 52 |
"encoding_name": null,
|