Instructions to use replicate/quantization-bitsandbytes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Kernels
How to use replicate/quantization-bitsandbytes with Kernels:
# !pip install kernels from kernels import get_kernel # a version (or an explicit revision) is required; see the "Files and versions" tab for the available ones kernel = get_kernel("replicate/quantization-bitsandbytes", version=1) - Notebooks
- Google Colab
- Kaggle
Download build/torch210-cxx11-cpu-x86_64-linux/metadata.json from replicate/quantization-bitsandbytes: direct link, hf CLI and curl.
- Browser
- Download file 190 Bytes
-
https://huggingface.co/replicate/quantization-bitsandbytes/resolve/main/build/torch210-cxx11-cpu-x86_64-linux/metadata.json
- Command line
-
hf download hf://replicate/quantization-bitsandbytes/build/torch210-cxx11-cpu-x86_64-linux/metadata.json
-
curl -L -o metadata.json https://huggingface.co/replicate/quantization-bitsandbytes/resolve/main/build/torch210-cxx11-cpu-x86_64-linux/metadata.json
190 Bytes
| { | |
| "name": "quantization-bitsandbytes", | |
| "id": "_quantization_bitsandbytes_cpu_817f262", | |
| "version": 1, | |
| "license": "MIT", | |
| "python-depends": [], | |
| "backend": { | |
| "type": "cpu" | |
| } | |
| } | |