Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
MIT License
Bot releases are visible (Hide)
Published by github-actions[bot] 9 months ago
Shipped with llama.cpp
release b1892
To use the latest
llama.cpp
release available, runnpx --no node-llama-cpp download --release latest
. (learn more)
Published by github-actions[bot] 9 months ago
Shipped with llama.cpp
release b1892
To use the latest
llama.cpp
release available, runnpx --no node-llama-cpp download --release latest
. (learn more)
Published by github-actions[bot] 9 months ago
llama.cpp
(#117) (595a6bc)x64
arch by default (#139) (5fcdf9b)LlamaChat
(#139) (5fcdf9b)LlamaText
util (#139) (5fcdf9b)llama.cpp
release in GitHub releases (#142) (36c779d)Shipped with llama.cpp
release b1892
To use the latest
llama.cpp
release available, runnpx --no node-llama-cpp download --release latest
(learn more)
Published by github-actions[bot] 11 months ago
Published by github-actions[bot] 12 months ago
CMAKE_GENERATOR_TOOLSET
for CUDA (#80) (ff1644d)Published by github-actions[bot] about 1 year ago
llama.cpp
changes (#60) (3400fce)chat
command (#62) (c0deffd)