app.py

import gradio as gr
import transformers
from transformers import AutoTokenizer
import torch
from diffusers.utils.torch_utils import randn_tensor

model = "Glasshes/debate_v3.1_model"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)


def debate_response(text):
    sequences = pipeline(
        "hello \n",
        do_sample=True,
        top_k=10,
        num_return_sequences=1,
        eos_token_id=tokenizer.eos_token_id,
        max_length=100,
    )
    print(sequences)
    return "testing"
    

intf = gr.Interface(fn=debate_response, inputs=gr.Textbox(), outputs="text")
intf.launch()