Instructions to use alexgusevski/saiga_gemma3_12b-mlx-8Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use alexgusevski/saiga_gemma3_12b-mlx-8Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir saiga_gemma3_12b-mlx-8Bit alexgusevski/saiga_gemma3_12b-mlx-8Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload chat_template.jinja with huggingface_hub
Browse files- chat_template.jinja +4 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
|
| 2 |
+
' }}{% if message['content'] is string %}{{ message['content'] | trim }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'image' %}{{ '<start_of_image>' }}{% elif item['type'] == 'text' %}{{ item['text'] | trim }}{% endif %}{% endfor %}{% endif %}{{ '<end_of_turn>
|
| 3 |
+
' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
|
| 4 |
+
'}}{% endif %}
|