Create app.py

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+MODEL_NAME = "OpenPeerAI/OpenPeerLLM"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype="auto")
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+def chat(prompt, max_new_tokens=256, temperature=0.7):
+    outputs = generator(
+        prompt,
+        max_new_tokens=max_new_tokens,
+        temperature=temperature,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    return outputs[0]['generated_text'][len(prompt):].strip()
+
+iface = gr.Interface(
+    fn=chat,
+    inputs=[
+        gr.Textbox(lines=4, label="Enter your prompt"),
+        gr.Slider(16, 1024, value=256, step=16, label="Max new tokens"),
+        gr.Slider(0.1, 1.5, value=0.7, step=0.05, label="Temperature")
+    ],
+    outputs="text",
+    title="OpenPeerLLM Text Demo",
+    description="Chat with OpenPeerLLM from HuggingFace!"
+)
+
+if __name__ == "__main__":
+    iface.launch()