How to use HelloSun/SmallThinker4b_EPQ with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="HelloSun/SmallThinker4b_EPQ", filename="{{GGUF_FILE}}", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
