bigger model

app.py

@@ -42,11 +42,12 @@ try:
     # Load Qwen 2.5 1.5B model with llama_cpp
     logger.info("Loading Qwen 2.5 1.5B model")
     model_path = hf_hub_download(
-        repo_id="Qwen/Qwen2.5-1.5B-Instruct-GGUF",
-        filename="qwen2.5-1.5b-instruct-q4_0.gguf",
+        repo_id="bartowski/Qwen2.5-7B-Instruct-GGUF", #"Qwen/Qwen2.5-1.5B-Instruct-GGUF",
+        filename="Qwen2.5-7B-Instruct-Q6_K.gguf", #"qwen2.5-1.5b-instruct-q4_0.gguf",
         local_dir="/app/cache" if os.getenv("HF_HOME") else None,
         token=hf_token,
     )
+
     generator = Llama(
         model_path=model_path,
         n_ctx=2048,