Skip to content

llamacpp-for-kobold-1.0.1
Compare
Choose a tag to compare
@LostRuins LostRuins released this 20 Mar 07:05
· 6905 commits to concedo since this release
v1.0.1
dda69d4

llamacpp-for-kobold-1.0.1

  • Bugfixes for OSX, and KV caching allows continuing a previous generation without reprocessing the whole prompt
  • Weights not included.

To use, download, extract and run (defaults port is 5001):
llama_for_kobold.py [ggml_quant_model.bin] [port]

and then you can connect like this (or use the full koboldai client):
https://lite.koboldai.net/?local=1&port=5001

Assets 3
Loading