Feature Extraction
MLX
Safetensors
ministral3
apple-silicon
quantized
mixed-precision
axquant
axq
development
mistral3
MXFP4
embedding
sentence-similarity
4-bit precision
Instructions to use AutomatosX/AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download AutomatosX/AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP4 --local-dir AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download sentence_bert_config.json from AutomatosX/AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP4: direct link, hf CLI and curl.
- Browser
- Download file 56 Bytes
-
https://huggingface.co/AutomatosX/AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP4/resolve/3769fdf1230a069d2629a135c8eddc6ab70c1cca/sentence_bert_config.json
- Command line
-
hf download hf://AutomatosX/AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP4@3769fdf1230a069d2629a135c8eddc6ab70c1cca/sentence_bert_config.json
-
curl -L -o sentence_bert_config.json https://huggingface.co/AutomatosX/AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP4/resolve/3769fdf1230a069d2629a135c8eddc6ab70c1cca/sentence_bert_config.json
56 Bytes
| { | |
| "max_seq_length": 32768, | |
| "do_lower_case": false | |
| } | |