Spaces:
Paused
Paused
File size: 1,528 Bytes
7d51224 1044c29 7d51224 1044c29 7d51224 c3fd9b2 1044c29 7d51224 1044c29 7d51224 1044c29 7d51224 1044c29 7d51224 1044c29 7d51224 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
import fastapi
import json
import markdown
import uvicorn
from ctransformers import AutoModelForCausalLM
from fastapi.responses import HTMLResponse
from fastapi.middleware.cors import CORSMiddleware
from sse_starlette.sse import EventSourceResponse
from ctransformers.langchain import CTransformers
from pydantic import BaseModel
from typing import List, Any
llm = AutoModelForCausalLM.from_pretrained("NeoDim/starchat-alpha-GGML",
model_file="starchat-alpha-ggml-q4_0.bin",
model_type="starcoder")
app = fastapi.FastAPI(title="Starchat Alpha")
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
@app.get("/")
async def index():
with open("README.md", "r", encoding="utf-8") as readme_file:
md_template_string = readme_file.read()
html_content = markdown.markdown(md_template_string)
return HTMLResponse(content=html_content, status_code=200)
class ChatCompletionRequest(BaseModel):
messages: List[Any]
@app.post("/v1/chat/completions")
async def chat(request: ChatCompletionRequest, response_mode=None):
tokens = llm.tokenize(request.messages)
async def server_sent_events(chat_chunks):
for token in llm.generate(chat_chunks):
yield llm.detokenize(token)
return EventSourceResponse(server_sent_events(tokens))
if __name__ == "__main__":
uvicorn.run(app, host="0.0.0.0", port=8000)
|