Instructions to use vinamrag-code/llama-cpp-python-cuda-wheels with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use vinamrag-code/llama-cpp-python-cuda-wheels with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="vinamrag-code/llama-cpp-python-cuda-wheels", filename="{{GGUF_FILE}}", )output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
Download llama_cpp_python-0.3.36-py3-none-linux_x86_64.whl from vinamrag-code/llama-cpp-python-cuda-wheels: direct link, hf CLI and curl.
- Browser
- Download file 271 MB
-
https://huggingface.co/vinamrag-code/llama-cpp-python-cuda-wheels/resolve/a6acce9b0a892d5e214bf8ed84fa2d8f602ab6d0/llama_cpp_python-0.3.36-py3-none-linux_x86_64.whl
- Command line
-
hf download hf://vinamrag-code/llama-cpp-python-cuda-wheels@a6acce9b0a892d5e214bf8ed84fa2d8f602ab6d0/llama_cpp_python-0.3.36-py3-none-linux_x86_64.whl
-
curl -L -o llama_cpp_python-0.3.36-py3-none-linux_x86_64.whl https://huggingface.co/vinamrag-code/llama-cpp-python-cuda-wheels/resolve/a6acce9b0a892d5e214bf8ed84fa2d8f602ab6d0/llama_cpp_python-0.3.36-py3-none-linux_x86_64.whl
271 MB
- Xet hash:
- de9e54bd8eaa84c2188847565765016b0499f18ed0e704d31d17428ba293c62d
- Size of remote file:
- 271 MB
- SHA256:
- 89034bc019d794122d91e6b703079cad91412c0061aa93fac1fec31200f53145
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.