app.py

import gradio as gr
from transformers import AutoTokenizer, pipeline
import torch

tokenizer1 = AutoTokenizer.from_pretrained("notexist/ttt")
tdk1 = pipeline('text-generation', model='notexist/ttt', tokenizer=tokenizer)
tokenizer2 = AutoTokenizer.from_pretrained("notexist/ttt")
tdk2 = pipeline('text-generation', model='notexist/ttt', tokenizer=tokenizer)

def predict(name, sl, topk, topp):
    if name == "":
        x1 = tdk1(f"<|endoftext|>",
            do_sample=True, 
            max_length=64, 
            top_k=topk, 
            top_p=topp, 
            num_return_sequences=1,
            repetition_penalty=sl
        )[0]["generated_text"]
        x2 = tdk1(f"<|endoftext|>",
            do_sample=True, 
            max_length=64, 
            top_k=topk, 
            top_p=topp, 
            num_return_sequences=1,
            repetition_penalty=sl
        )[0]["generated_text"]

        return x1[len(f"<|endoftext|>"):]+"\n\n"+x2[len(f"<|endoftext|>"):]
    else:
        x1 = tdk1(f"<|endoftext|>{name}\n\n",
            do_sample=True, 
            max_length=64, 
            top_k=topk, 
            top_p=topp, 
            num_return_sequences=1,
            repetition_penalty=sl
        )[0]["generated_text"]
        x2 = tdk2(f"<|endoftext|>{name}\n\n",
            do_sample=True, 
            max_length=64, 
            top_k=topk, 
            top_p=topp, 
            num_return_sequences=1,
            repetition_penalty=sl
        )[0]["generated_text"]

        return x1[len(f"<|endoftext|>{name}\n\n"):]+"\n\n"+x2[len(f"<|endoftext|>{name}\n\n"):]



iface = gr.Interface(fn=predict, inputs=["text",\
                                         gr.inputs.Slider(0, 3, default=1.1, label="repetition_penalty"),\
                                         gr.inputs.Slider(0, 100, default=75, label="top_k"),\
                                         gr.inputs.Slider(0, 1, default=0.95, label="top_p")]
                     , outputs="text")
iface.launch()