import gradio as gr
import json
import requests
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = 'Pyg'
tokenizer = AutoTokenizer.from_pretrained("TheBloke/Pygmalion-7B-SuperHOT-8K-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Pygmalion-7B-SuperHOT-8K-GPTQ")

pipe = pipeline("text-generation", model="TheBloke/Pygmalion-7B-SuperHOT-8K-GPTQ")

def generate_text(input_text):
    input_ids = tokenizer.encode(input_text, return_tensors='pt')
    outputs = model.generate(input_ids, max_length=150, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
    text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return text

iface = gr.Interface(fn=generate_text, 
                      inputs=gr.inputs.Textbox(lines=5, placeholder='Enter text here...'), 
                      outputs=gr.outputs.Textbox())

iface.launch()