Instructions to use mlx-community/Jan-v2-VL-med-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Jan-v2-VL-med-4bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Jan-v2-VL-med-4bit-mlx mlx-community/Jan-v2-VL-med-4bit-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Invalid eos_token_id type
Browse filesThis causes an issue while running with mlx-swift, the eos_token_id should be an array or null.
- config.json +1 -1
config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"Qwen3VLForConditionalGeneration"
|
| 4 |
],
|
| 5 |
"dtype": "float32",
|
| 6 |
-
"eos_token_id":
|
| 7 |
"image_token_id": 151655,
|
| 8 |
"model_type": "qwen3_vl",
|
| 9 |
"pad_token_id": 151643,
|
|
|
|
| 3 |
"Qwen3VLForConditionalGeneration"
|
| 4 |
],
|
| 5 |
"dtype": "float32",
|
| 6 |
+
"eos_token_id": null,
|
| 7 |
"image_token_id": 151655,
|
| 8 |
"model_type": "qwen3_vl",
|
| 9 |
"pad_token_id": 151643,
|