Update app.py

app.py

@@ -1,32 +1,30 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Use HF's inference API - no local model needed!
-client = InferenceClient(
-    model="bartowski/p-e-w_Qwen3-4B-Instruct-2507-heretic-GGUF"
-)
+# Use the uncensored Llama model
+client = InferenceClient(model="Orenguteng/Llama-3-8B-Lexi-Uncensored")
 
 def chat(message, history):
-    # Build conversation from history
     messages = []
     for human, assistant in history:
         messages.append({"role": "user", "content": human})
         messages.append({"role": "assistant", "content": assistant})
     messages.append({"role": "user", "content": message})
     
-    # Stream the response
     response = ""
-    for chunk in client.chat_completion(
-        messages=messages,
-        max_tokens=512,
-        temperature=0.7,
-        stream=True
-    ):
-        if chunk.choices[0].delta.content:
-            response += chunk.choices[0].delta.content
-            yield response
+    try:
+        for chunk in client.chat_completion(
+            messages=messages,
+            max_tokens=512,
+            temperature=0.7,
+            stream=True
+        ):
+            if chunk.choices[0].delta.content:
+                response += chunk.choices[0].delta.content
+                yield response
+    except Exception as e:
+        yield f"Error: {str(e)}"
 
-# Create the chat interface
 demo = gr.ChatInterface(
     chat,
     type="messages",