Views
No views yet
q4f32_1.
The model can be used with MLC-LLM and WebLLM.mlc_llm chat HF://JackBinary/Cydonia-v1.3-Magnum-v4-22B-q4f32_1-MLCmlc_llm serve HF://JackBinary/Cydonia-v1.3-Magnum-v4-22B-q4f32_1-MLC1from mlc_llm import MLCEngine
2
3model = "HF://JackBinary/Cydonia-v1.3-Magnum-v4-22B-q4f32_1-MLC"
4engine = MLCEngine(model)
5
6for response in engine.chat.completions.create(
7 messages=[{"role": "user", "content": "What is the meaning of life?"}],
8 model=model,
9 stream=True,
10):
11 for choice in response.choices:
12 print(choice.delta.content, end="", flush=True)
13print("\n")
14
15engine.terminate()