Create app.py

app.py

@@ -0,0 +1,32 @@
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "your-username/my-wizardmath-finetuned"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id,
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    device_map="auto"
+)
+
+def generate_answer(prompt, max_new_tokens=256, temperature=0.7, top_p=0.95):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens=max_new_tokens,
+                                 temperature=temperature, top_p=top_p,
+                                 do_sample=True, pad_token_id=tokenizer.eos_token_id)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+gr.Interface(
+    fn=generate_answer,
+    inputs=[
+      gr.Textbox(label="Prompt"),
+      gr.Slider(50, 1024, value=256, step=1, label="Max Tokens"),
+      gr.Slider(0.1, 1.0, value=0.7, step=0.05, label="Temperature"),
+      gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top‑p")
+    ],
+    outputs=gr.Textbox(label="Response"),
+    title="WizardMath Demo",
+    description="Ask your fine‑tuned WizardMath model math questions!",
+).launch()