No support for making GGUF of HuggingFaceTB/SmolVLM-500M-Instruct

#148
by TimexPeachtree - opened

Error converting to fp16: INFO:hf-to-gguf:Loading model: SmolVLM-500M-Instruct
ERROR:hf-to-gguf:Model Idefics3ForConditionalGeneration is not supported

The model is not supported by llama.cpp yet, quantizing it won't work until it is implemented.

Two related issues on github:
https://github.com/ggerganov/llama.cpp/issues/10877
https://github.com/ggerganov/llama.cpp/issues/11682

Sign up or log in to comment