update to lama:3.2

Dockerfile

@@ -42,4 +42,4 @@ USER 1000
 EXPOSE 7860
 
 # Startup command
-CMD sh -c "ollama serve & sleep 5 && ollama pull llama3.2:1b && uvicorn main:app --host 0.0.0.0 --port 7860 --timeout-keep-alive 65"
+CMD sh -c "ollama serve & sleep 5 && ollama pull llama3.2 && uvicorn main:app --host 0.0.0.0 --port 7860 --timeout-keep-alive 65"

main.py

@@ -79,7 +79,7 @@ async def get_full_voice_and_text(payload, voice, rate):
 @app.post("/stream-voice")
 async def voice_engine(data: ChatRequest):
     payload = {
-        "model": "llama3.2:1b",
+        "model": "llama3.2",
         "messages": data.messages,
         "stream": False, # Set to False for non-streaming
         "options": {