Update main.py

main.py

@@ -3,7 +3,7 @@ import json
 import markdown
 import uvicorn
 from fastapi import HTTPException
-from fastapi.responses import HTMLResponse, HTTPException
+from fastapi.responses import HTMLResponse
 from fastapi.middleware.cors import CORSMiddleware
 from sse_starlette.sse import EventSourceResponse
 from ctransformers import AutoModelForCausalLM
@@ -14,7 +14,7 @@ from typing import List, Dict, Any
 llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardCoder-15B-1.0-GGML",
                                            model_file="WizardCoder-15B-1.0.ggmlv3.q4_0.bin",
                                            model_type="starcoder")
-app = fastapi.FastAPI(title="WizardCoder")
+app = fastapi.FastAPI(title="🪄WizardCoder💫")
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
@@ -59,7 +59,7 @@ async def completion(request: ChatCompletionRequest, response_mode=None):
     response = llm(request.prompt)
     return response
 
-@app.post("/v2/chat/completions")
+@app.post("/v1/chat/completions")
 async def chat(request: ChatCompletionRequestV2):
     tokens = llm.tokenize([message.content for message in request.messages])
     
@@ -84,7 +84,7 @@ async def chat(request: ChatCompletionRequestV2):
 
     return format_response(chat_chunks)
 
-@app.post("/v1/chat/completions")
+@app.post("/v0/chat/completions")
 async def chat(request: ChatCompletionRequest, response_mode=None):
     tokens = llm.tokenize(request.prompt)
     async def server_sent_events(chat_chunks, llm):