app.py

from ctransformers import AutoModelForCausalLM
import gradio as gr
from fastapi import FastAPI, Form
from pydantic import BaseModel

#Model loading
llm = AutoModelForCausalLM.from_pretrained("mistral-7b-openorca.Q4_K_S.gguf",
model_type='mistral',
max_new_tokens = 1096,
threads = 3,
)
   

#Pydantic object
class validation(BaseModel):
    prompt: str
    
#Fast API
app = FastAPI()


@app.post("/llm_on_cpu")
async def stream(item: validation):
    system_prompt = 'Below is an instruction that describes a task. Write a response that appropriately completes the request. Write only in ITALIAN.'
    E_INST = "</s>"
    user, assistant = "<|user|>", "<|assistant|>"
    prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt.strip()}{E_INST}\n{assistant}\n"
    return llm(prompt)


greety = """
Test
"""


css = """
  h1 {
  text-align: center;
}
#duplicate-button {
  margin: auto;
  color: white;
  background: #1565c0;
  border-radius: 100vh;
}
.contain {
  max-width: 900px;
  margin: auto;
  padding-top: 1.5rem;
}
"""

chat_interface = gr.ChatInterface(
    fn=stream,
    stop_btn=None,
    examples=[
        ["explain Large language model"],
        ["what is quantum computing"]
    ],
)

with gr.Blocks(css=css) as demo:
    gr.HTML("<h1><center>LLM Deployment Space<h1><center>")
    gr.HTML("<h3><center><a href='#'>AI</a>💬<h3><center>")
    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
    chat_interface.render()
    gr.Markdown(greety)
    
if __name__ == "__main__":
    demo.queue(max_size=10).launch()