v3: 修 MAP_POPULATE 與 /proc/self/io 解析 bug;A/B 驗證工具;輸出逐字相同已證實 1e54449
Auto Upload Agent commited on
How to use HelloSun/SmallThinker4b with llama-cpp-python:
# !pip install llama-cpp-python
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="HelloSun/SmallThinker4b",
filename="{{GGUF_FILE}}",
)
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)