unlike the source model, I can't gguf this. tokenizer not supported
#1
by MikaSouthworth - opened
did you change the tokenizer more than required? llama.cpp does not recognize it any more, unlike the source model from qwen
I need to read the full output ;D
pip install git+https://github.com/huggingface/transformers.git <---- do this in your mamba/conda env and it works.... I am sure (I HOPE!!!) I am not the only one making this mistake 🫥
so apologies, but I let this thread stand here for others to see the solution
