Update agent.py

agent.py

@@ -684,6 +684,7 @@ def build_graph(provider: str = "huggingface"):
                 #endpoint_url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
                 #endpoint_url="https://api-inference.huggingface.co/models/Qwen/Qwen3-30B-A3B",
                 endpoint_url="https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B.Instruct",
+                #endpoint_url="https://api-inference.huggingface.co/models/Qwen/Qwen3-4B",
                 temperature=0,
             ),
         )
@@ -692,10 +693,8 @@ def build_graph(provider: str = "huggingface"):
             llm=HuggingFaceEndpoint(
                 #repo_id="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
                 #endpoint_url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
-                #endpoint_url="https://api-inference.huggingface.co/models/Qwen/Qwen3-4B",
-                endpoint_url="https://api-inference.huggingface.co/models/microsoft/phi-4",
-                token=https://huggingface.co/spaces/IamRulo/Final_Assignment_Template/settings/HF_TOKEN,
-                
+                #endpoint_url="https://api-inference.huggingface.co/models/microsoft/phi-4",
+                endpoint_url="https://api-inference.huggingface.co/models/TinyLlama/TinyLlama-1.1B-Chat-v1.0",
                 #task="text-generation",  # for chat‐style use “text-generation”
                 #max_new_tokens=1024,
                 #do_sample=False,