feat(nlp): switch Qwen2.5 model to 1.5B GGUF q6_k version

app/routes/nlp.py

@@ -24,13 +24,11 @@ class ChatRequest(BaseModel):
 
 # Load NLP model
 def load_model_nlp():
+
     llm = Llama.from_pretrained(
-        repo_id="Qwen/Qwen2.5-3B-Instruct-GGUF",
-        filename="qwen2.5-3b-instruct-q5_0.gguf",
-        n_ctx=2048,
-        verbose=False
+        repo_id="Qwen/Qwen2.5-1.5B-Instruct-GGUF",
+        filename="qwen2.5-1.5b-instruct-q6_k.gguf",
     )
-    print("[INFO] NLP model loaded.")
     return llm
 
 @router.post("/chat")