from llama_cpp import Llama
import gradio as gr

model_path = "matrixportal/Mistral-7B-Instruct-v0.3-Q4_K_M-GGUF"  # Update with the correct filename

llm = Llama(model_path=model_path, n_ctx=2048, n_threads=8)

def chat_response(prompt):
    output = llm(prompt, max_tokens=200, temperature=0.7)
    return output["choices"][0]["text"]

iface = gr.Interface(fn=chat_response, inputs="text", outputs="text")
iface.launch()