GGUF Request - LFM2-ColBERT-350M

#1488
by cnmoro - opened

It would be interesting to run some experiments with this one

https://huggingface.co/LiquidAI/LFM2-ColBERT-350M

The Lfm2Model architecture used by this model is not yet supported by llama cpp. Because of this it is unfortunately not currently possible to convert this model into a GGUF:

INFO:hf-to-gguf:Loading model: LFM2-ColBERT-350M
INFO:hf-to-gguf:Model architecture: Lfm2Model
ERROR:hf-to-gguf:Model Lfm2Model is not supported

Sign up or log in to comment