Ollama can take a model file and create an LLM from it. Can someone posts some websites to help me learn to do that? I can also program in Python 3.11 on Windows 11.
Thanks.
1 Like
Ollama uses GGUF format files. There are several methods for quantizing Hugging Face’s Transoformers format to GGUF, but using the conversion script included with Llama.cpp is relatively simple.