Create app.py

app.py

@@ -0,0 +1,28 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "ayyuce/SmolGRPO-135M"
+
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+model.to("cpu") 
+
+def generate_text(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    inputs = {key: value.to("cpu") for key, value in inputs.items()}
+    outputs = model.generate(**inputs, max_length=100, do_sample=True, top_p=0.95, top_k=50)
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return generated_text
+
+demo = gr.Interface(
+    fn=generate_text,
+    inputs="text",
+    outputs="text",
+    title="SmolGRPO-135M Generator",
+    description="Generate text with the SmolGRPO-135M."
+)
+
+if __name__ == "__main__":
+    demo.launch()