Update main.py

main.py

@@ -5,13 +5,11 @@ import uvicorn
 from fastapi.responses import HTMLResponse
 from fastapi.middleware.cors import CORSMiddleware
 from sse_starlette.sse import EventSourceResponse
-from ctransformers import AutoModelForCausalLM
+from ctransformers.langchain import CTransformers
 from pydantic import BaseModel
 
-llm = AutoModelForCausalLM.from_pretrained("danforbes/santacoder-ggml-q4_1",
-                                           model_file="santacoder-ggml-q4_1.bin",
-                                           model_type="starcoder")
-app = fastapi.FastAPI()
+llm = CTransformers(model='ggml-model-q4_1.bin', model_type='starcoder')
+app = fastapi.FastAPI(title="Santacoder")
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
@@ -32,14 +30,13 @@ class ChatCompletionRequest(BaseModel):
 
 @app.post("/v1/chat/completions")
 async def chat(request: ChatCompletionRequest, response_mode=None):
-    tokens = llm.tokenize(request.prompt)
-    async def server_sent_events(chat_chunks, llm):
-        for token in llm.generate(chat_chunks):
-            yield dict(data=llm.detokenize(token))
+    completion = llm(request.prompt)
+    async def server_sent_events(chat_chunks):
+        for chat_chunk in chat_chunks:
+            yield dict(data=json.dumps(chat_chunk))
         yield dict(data="[DONE]")
 
-    return EventSourceResponse(server_sent_events(tokens, llm))
+    return EventSourceResponse(server_sent_events(completion))
 
 if __name__ == "__main__":
-  uvicorn.run(app, host="0.0.0.0", port=8000)
-
+  uvicorn.run(app, host="0.0.0.0", port=8000)