Text Classification
MLX
Safetensors
lfm3_vl
optiq
quantized
4bit
mixed-precision
liquid
lfm3
decision
decision-model
classification
calibration
system-one
typed-decisions
apple-silicon
custom_code
Eval Results
4-bit precision
Instructions to use mlx-community/d1-2B-OptiQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/d1-2B-OptiQ-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/d1-2B-OptiQ-4bit --local-dir d1-2B-OptiQ-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download tokenizer.json from mlx-community/d1-2B-OptiQ-4bit: direct link, hf CLI and curl.
- Browser
- Download file 17.9 MB
-
https://huggingface.co/mlx-community/d1-2B-OptiQ-4bit/resolve/main/tokenizer.json
- Command line
-
hf download hf://mlx-community/d1-2B-OptiQ-4bit/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/mlx-community/d1-2B-OptiQ-4bit/resolve/main/tokenizer.json
17.9 MB
- Xet hash:
- 0c6ae2ae860eab63090922b6595184b27e5518f7caaa263b8c10fd8c3bb367e3
- Size of remote file:
- 17.9 MB
- SHA256:
- a39eed58008cbcbc09e5b629b81338a654269c64cd13348aaa6090f4db75c7e7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.