hackathon / main.py
hArshi07's picture
main.py
a316563
raw
history blame contribute delete
859 Bytes
from ctransformers import AutoModelForCausalLM
from fastapi import FastAPI
from pydantic import BaseModel
llm = AutoModelForCausalLM.from_pretrained("TheBloke/CodeLlama-7B-Instruct-GGUF",
model_file="codellama-7b-instruct.q4_K_M.gguf",
model_type="llama",
gpu_layers=0)
#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.'
E_INST = "</s>"
user, assistant = "<|user|>", "<|assistant|>"
prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt}{E_INST}\n{assistant}\n"
return llm(prompt)