app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/SOLAR-10.7B-Instruct-v1.0-uncensored-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/SOLAR-10.7B-Instruct-v1.0-uncensored-GPTQ")

def generate_response(prompt):
    conversation = [{'role': 'user', 'content': prompt}]
    prompt = tokenizer.apply_chat_template(conversation, tokenizer=False, add_generation_prompt=True)
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, use_cache=True, max_length=4096)
    outputs_text = tokenizer.decode(outputs[0])
    return outputs_text

iface = gr.Interface(fn=generate_response, inputs="text", outputs="text")
iface.launch()