Multiple Choice
MLX
Safetensors
English
Russian
qwen3_5
decision-model
vision
experimental
4-bit precision
Instructions to use r3lax/sys1mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use r3lax/sys1mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir sys1mlx r3lax/sys1mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download validation.json from r3lax/sys1mlx: direct link, hf CLI and curl.
- Browser
- Download file 2.26 kB
-
https://huggingface.co/r3lax/sys1mlx/resolve/main/validation.json
- Command line
-
hf download hf://r3lax/sys1mlx/validation.json
-
curl -L -o validation.json https://huggingface.co/r3lax/sys1mlx/resolve/main/validation.json
2.26 kB
| { | |
| "description": "Packaging smoke check on M4; illustrative examples, not a quality benchmark", | |
| "results": [ | |
| { | |
| "mode": "text", | |
| "seconds": 0.2356886670000904, | |
| "result": { | |
| "answers": { | |
| "color": { | |
| "type": "choice", | |
| "choice": "red", | |
| "confidence": 1.0, | |
| "probabilities": { | |
| "red": 1.0, | |
| "blue": 0.0, | |
| "green": 0.0 | |
| } | |
| } | |
| }, | |
| "probabilities": [ | |
| [ | |
| 0.9999960660934448, | |
| 2.600952939246781e-06, | |
| 1.2866769338870654e-06 | |
| ] | |
| ], | |
| "input_tokens": 29, | |
| "vision": null | |
| } | |
| }, | |
| { | |
| "mode": "vision", | |
| "seconds": 0.7187503750000133, | |
| "result": { | |
| "answers": { | |
| "color": { | |
| "type": "choice", | |
| "choice": "red", | |
| "confidence": 1.0, | |
| "probabilities": { | |
| "red": 1.0, | |
| "blue": 0.0, | |
| "green": 0.0 | |
| } | |
| } | |
| }, | |
| "probabilities": [ | |
| [ | |
| 0.9999994039535522, | |
| 3.513019066758716e-07, | |
| 2.60039115573818e-07 | |
| ] | |
| ], | |
| "input_tokens": 176, | |
| "vision": { | |
| "tokens": 144, | |
| "source_size": [ | |
| 384, | |
| 384 | |
| ], | |
| "processed_size": [ | |
| 384, | |
| 384 | |
| ] | |
| } | |
| } | |
| }, | |
| { | |
| "mode": "repeat", | |
| "seconds": 0.4666795829999728, | |
| "result": { | |
| "answers": { | |
| "color": { | |
| "type": "choice", | |
| "choice": "red", | |
| "confidence": 1.0, | |
| "probabilities": { | |
| "red": 1.0, | |
| "blue": 0.0, | |
| "green": 0.0 | |
| } | |
| } | |
| }, | |
| "probabilities": [ | |
| [ | |
| 0.9999994039535522, | |
| 3.513019066758716e-07, | |
| 2.60039115573818e-07 | |
| ] | |
| ], | |
| "input_tokens": 176, | |
| "vision": { | |
| "tokens": 144, | |
| "source_size": [ | |
| 384, | |
| 384 | |
| ], | |
| "processed_size": [ | |
| 384, | |
| 384 | |
| ] | |
| } | |
| } | |
| } | |
| ] | |
| } | |