Instructions to use mlx-community/nanoLLaVA-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/nanoLLaVA-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir nanoLLaVA-4bit mlx-community/nanoLLaVA-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Update config.json
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"auto_map": {
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"BunnyQwenForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_dropout": 0.0,
|
| 6 |
"auto_map": {
|