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 kernel = get_kernel("replicate/quantization-bitsandbytes") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from replicate/quantization-bitsandbytes: direct link, hf CLI and curl.
- Browser
- Download file 648 Bytes
-
https://huggingface.co/replicate/quantization-bitsandbytes/resolve/b7b14ac6d8ccab167f540bde1ef6cbd06acf6d9e/README.md
- Command line
-
hf download hf://replicate/quantization-bitsandbytes@b7b14ac6d8ccab167f540bde1ef6cbd06acf6d9e/README.md
-
curl -L -o README.md https://huggingface.co/replicate/quantization-bitsandbytes/resolve/b7b14ac6d8ccab167f540bde1ef6cbd06acf6d9e/README.md
648 Bytes
| library_name: kernels | |
| license: mit | |
| This is the repository card of kernels-community/quantization-bitsandbytes that has been pushed on the Hub. It was built to be used with the [`kernels` library](https://github.com/huggingface/kernels). This card was automatically generated. | |
| ## How to use | |
| ```python | |
| # make sure `kernels` is installed: `pip install -U kernels` | |
| from kernels import get_kernel | |
| kernel_module = get_kernel("kernels-community/quantization-bitsandbytes") | |
| gemm_4bit_forward = kernel_module.gemm_4bit_forward | |
| gemm_4bit_forward(...) | |
| ``` | |
| ## Available functions | |
| - `gemm_4bit_forward` | |
| ## Benchmarks | |
| No benchmark available yet. | |