node-llama-cpp
node-llama-cpp copied to clipboard
feat: split gguf files support
Description of change
- feat: split gguf files support
- feat:
pullcommand - feat:
stopOnAbortSignalandcustomStopTriggersonLlamaChatandLlamaChatSession - feat:
checkTensorsparameter onloadModel - fix: more efficient max context size finding algorithm
- fix: make embedding-only models work correctly
- fix: perform context shift on the correct token index on generation
- docs: update Vitepress, add code type information on hover
- docs: update simple usage
Fixes #211
Pull-Request Checklist
- [x] Code is up-to-date with the
masterbranch - [x]
npm run formatto apply eslint formatting - [x]
npm run testpasses with this change - [x] This pull request links relevant issues as
Fixes #0000 - [x] There are new or updated unit tests validating the change
- [ ] Documentation has been updated to reflect this change
- [x] The new commits and pull request title follow conventions explained in pull request guidelines (PRs that do not follow this convention will not be merged)