search

InftyAI / llmlite

🌵 A library helps to communicate with all kinds of LLMs consistently.
MIT License
6 stars 2 forks source link

Support loading different adapter #51

Open kerthcet opened 6 months ago

kerthcet commented 6 months ago

Generally the API looks like

chat = ChatLLM(
    model_name_or_path="meta-llama/Llama-2-7b-chat-hf", # required
    task="text-generation",
    adapter=<path/to/adapter>, # optional
    )