Create app.py

app.py

@@ -0,0 +1,20 @@
+import gradio as gr
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+import torch
+
+tokenizer = GPT2Tokenizer.from_pretrained("AlphaMindQ/GPTx-v6-60gb")
+model = GPT2LMHeadModel.from_pretrained("AlphaMindQ/GPTx-v6-60gb")
+model.eval()
+torch.set_num_threads(2)
+
+def generate(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(inputs["input_ids"], max_new_tokens=50)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+gr.Interface(fn=generate, 
+             inputs=gr.Textbox(label="Enter prompt"), 
+             outputs=gr.Textbox(label="Generated text"),
+             title="AlphaMindQ - GPTx-v6-60gb",
+             description="Tiny GPT-2-compatible model demo"
+).launch()