File size: 345 Bytes
22e1d30 c97127b 22e1d30 c97127b 22e1d30 c97127b 22e1d30 |
1 2 3 4 5 6 7 8 9 10 11 12 |
import gradio as gr
from llama_cpp import Llama
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="LLukas22/gpt4all-lora-quantized-ggjt", filename="ggjt-model.bin", local_dir=".")
llm = Llama(model_path="./ggjt-model.bin")
def chat(input):
return llm(input)
gr.Interface(fn=chat, inputs="text", outputs="text").launch() |