how to finetune and quantize the qwen1.5 model with gguf

#5
by huntz47 - opened

i am new in here. i tried finetuning the qwen model and and quantized it using llama factory and llama.cpp. but when i try to run the gguf file after quantizing, its getting error related to missing output.weight tensor file

Qwen org

It only happens to the 0.5B models which uses tie word embedings.
A fix has been merged: https://github.com/ggerganov/llama.cpp/pull/6738

jklj077 changed discussion status to closed

Sign up or log in to comment