How can use GOT-OCR2_0 on vLLM or Ollama?
#35
by
MhmdSyd
- opened
I want to convert the model file that type is safetensors to GUFF using llama.cpp to can run model on Ollama or vLLM.
But there is an issue that architecture of model is GOTQwenForCausalLM and llama.cpp is not support this architecture.
here the error:
INFO:hf-to-gguf:Loading model: GOT-OCR2_0
ERROR:hf-to-gguf:Model GOTQwenForCausalLM is not supported
if can any one support!!!
