When using RisuAI 136.0.1 as the frontend with a Yi 34B based model, text generation will cut off after around 400-500 tokens. Terminal shows the error message: "Token streaming was interrupted or aborted! [Errno 32] Broken pipe". Streaming is enabled in Risu, max response tokens is set to 4096, and API selected is OpenAI-compatible.
Kobold.cpp is version 1.76 (although this also happened with the previous version), started with the command line "./koboldcpp-linux-x64-nocuda --usevulkan --gpulayers 24 --threads 7 --contextsize 8192".
On up-to-date openSuse Tumbleweed, i7-12700KF cpu with 32GB DDR4 RAM and AMD RX 6800 card.
When using RisuAI 136.0.1 as the frontend with a Yi 34B based model, text generation will cut off after around 400-500 tokens. Terminal shows the error message: "Token streaming was interrupted or aborted! [Errno 32] Broken pipe". Streaming is enabled in Risu, max response tokens is set to 4096, and API selected is OpenAI-compatible.
Kobold.cpp is version 1.76 (although this also happened with the previous version), started with the command line "./koboldcpp-linux-x64-nocuda --usevulkan --gpulayers 24 --threads 7 --contextsize 8192".
On up-to-date openSuse Tumbleweed, i7-12700KF cpu with 32GB DDR4 RAM and AMD RX 6800 card.