Create app.py

app.py

@@ -0,0 +1,41 @@
+import gradio as gr
+import torch
+from transformers import pipeline
+
+pipe = pipeline("text-generation", 
+                model="HuggingFaceH4/zephyr-7b-beta", 
+                torch_dtype=torch.bfloat16, 
+                device_map="auto")
+
+
+def generate_response(user_input):
+    # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a friendly chatbot who always responds in the style of a pirate",
+        },
+        {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
+    ]
+    # prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    prompt = "How many helicopters can a human eat in one sitting?"
+    outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+    print(outputs[0]["generated_text"])
+    return outputs[0]["generated_text"]
+    
+# <|system|>
+# You are a friendly chatbot who always responds in the style of a pirate.</s>
+# <|user|>
+# How many helicopters can a human eat in one sitting?</s>
+# <|assistant|>
+# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
+
+iface = gr.Interface(
+    fn=generate_response,
+    inputs = gr.Textbox(lines=3, placeholder="Enter your message here ..."),
+    outputs = "text",
+    title = "Chat with Meta-Llama-Guard-2-8B",
+    description = "A Gradio interface to interact with the Meta-Llama-Guard-2-8B model for safe chat moderation."
+)
+
+iface.launch()