Spaces:
Sleeping
Sleeping
Update main.py
Browse files
main.py
CHANGED
@@ -8,10 +8,11 @@ app = FastAPI()
|
|
8 |
llm = None
|
9 |
|
10 |
def start_llm():
|
|
|
11 |
llm = Llama(model_path="./tinyllama-1.1b-chat.gguf")
|
12 |
|
13 |
-
|
14 |
@app.post("/health")
|
|
|
15 |
return {"status": "ok"}
|
16 |
|
17 |
@app.post("/deployllm")
|
@@ -29,5 +30,4 @@ async def stream(item: dict):
|
|
29 |
|
30 |
return llm(prompt, max_tokens=max_tokens, temperature=temperatura)
|
31 |
|
32 |
-
|
33 |
-
threading.Thread(target=start_llm).start()
|
|
|
8 |
llm = None
|
9 |
|
10 |
def start_llm():
|
11 |
+
global llm # Adicione esta linha para modificar a variável global
|
12 |
llm = Llama(model_path="./tinyllama-1.1b-chat.gguf")
|
13 |
|
|
|
14 |
@app.post("/health")
|
15 |
+
def health_check():
|
16 |
return {"status": "ok"}
|
17 |
|
18 |
@app.post("/deployllm")
|
|
|
30 |
|
31 |
return llm(prompt, max_tokens=max_tokens, temperature=temperatura)
|
32 |
|
33 |
+
threading.Thread(target=start_llm).start()
|
|