koboldcpp/prompts/chat-with-qwen.txt at 3fec68be4e9577fc53158366d3b3af039c17bb1f - koboldcpp - Gitea: Git with a cup of coffee

Public/koboldcpp

mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-03 03:21:24 +02:00

Files

T

Shijie 37c746d687 llama : add Qwen support (#4281 )

* enable qwen to llama.cpp

* llama : do not GPU split bias tensors

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2023-12-01 20:16:31 +02:00

1 line

28 B

Plaintext

Raw Blame History

You are a helpful assistant.