Update app.py

app.py

@@ -5,8 +5,9 @@ from huggingface_hub import InferenceClient
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 #client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-client = InferenceClient("meta-llama/Llama-3.3-70B-Instruct")
-
+#client = InferenceClient("meta-llama/Llama-3.2-1B-Instruct")
+#client = InferenceClient("microsoft/Phi-3.5-mini-instruct")
+client = InferenceClient("unsloth/Llama-3.2-1B-Instruct")
 
 
 def respond(
@@ -29,47 +30,16 @@ def respond(
 
     response = ""
 
-    try:
-        for message in client.chat_completion(
-            messages,
-            max_tokens=max_tokens,
-            stream=True,
-            temperature=temperature,
-            top_p=top_p,
-        ):
-            # Ensure the message has a valid structure
-            if not message or not isinstance(message, dict):
-                continue
-            
-            try:
-                # Extract content and finish reason
-                content = message.choices[0].delta.content
-                finish_reason = message.choices[0].finish_reason
-
-                # Check if the content is empty
-                if content.strip() == "":
-                    # If the finish reason is 'stop', it's expected and we can break the loop
-                    if finish_reason == "stop":
-                        print("Stream ended normally.")
-                        break
-                    else:
-                        print("Received unexpected empty content, skipping...")
-                        continue
-
-                response += content
-                yield response
-
-            except (AttributeError, IndexError, KeyError) as e:
-                print(f"Error processing message: {e}")
-                continue
 
-    except Exception as e:
-        print(f"Unexpected error: {e}")
-        yield "An error occurred while generating the response."
+    mensagens = client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+    )
+    response = mensagens.choices[0].message.content
 
-    # Final check if the response is empty
-    if response.strip() == "":
-        yield "No response generated. Please try again or adjust the settings."
+    return response
 
 
 """
@@ -78,7 +48,7 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a friendly Chatbot. Your name is Juninho.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
@@ -93,4 +63,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()