unsloth bnb 4bits

app.py

@@ -160,10 +160,10 @@ if __name__ == "__main__":
     # you can use HFApiModel from smolagents if you don't mind paying more money.
     model = TransformersModel(
         # model_id="Qwen/Qwen2.5-Coder-14B-Instruct",
-        model_id="unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit",
+        # model_id="unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit",
+model_id = "MaziyarPanahi/Llama-3.2-3B-Instruct-GGUF",
         device_map="cuda"
     )
-    model.model.to("cuda")
     # model = HfApiModel(
         # model_id="meta-llama/Meta-Llama-3.1-8B-Instruct",
         # token = os.getenv("bakery_multi_agents_hf_tokens_write")