Create app.py

app.py

@@ -0,0 +1,47 @@
+import gradio as gr
+
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+
+def generate(text, model, tokenizer,device,do_sample,top_k=100, epsilon_cutoff=.00005, temperature=1):
+    #mark the text with special tokens
+    text=[tokenizer.eos_token +  i + tokenizer.eos_token for i in text]
+    batch=tokenizer(text, padding=True, return_tensors="pt")
+
+    input_ids = batch["input_ids"].to(device)
+    attention_mask = batch["attention_mask"].to(device)
+
+    #how many new tokens to generate at max
+    max_prompt_length=50
+
+    generated_ids = model.generate(input_ids=input_ids,attention_mask=attention_mask, max_new_tokens=max_prompt_length, do_sample=do_sample,top_k=top_k, epsilon_cutoff=epsilon_cutoff, temperature=temperature)
+    #return only the generated prompts
+    pred_caps = tokenizer.batch_decode(generated_ids[:, -(generated_ids.shape[1] - input_ids.shape[1]):], skip_special_tokens=True)
+
+    return pred_caps
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+model = GPT2LMHeadModel.from_pretrained('fittar/ViPE-M-CTX7')
+model.to(device)
+tokenizer = GPT2Tokenizer.from_pretrained('gpt2-medium')
+tokenizer.pad_token = tokenizer.eos_token
+
+
+def generate(text):
+    result = gprompts=generate(text,model,tokenizer,do_sample=True,device=device)
+    return result
+
+examples = [
+    ["Is string theory right?"],
+    ["She felt like a flower in December"],
+    ["2+2=4?"],
+]
+
+demo = gr.Interface(
+    fn=generate,
+    inputs=gr.inputs.Textbox(lines=5, label="Input Text"),
+    outputs=gr.outputs.Textbox(label="Generated Text"),
+    examples=examples
+)
+
+demo.launch()