import os
import torch
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM, QuantoConfig

access_token = os.environ["GATED_ACCESS_TOKEN"]

quantization_config = QuantoConfig(
    weights = "int4"
)

model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", quantization_config=quantization_config, device_map="auto", token=access_token)
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")

# Load the tokenizer and model
#model_id = "mistralai/Mixtral-8x7B-v0.1"
#tokenizer = AutoTokenizer.from_pretrained(model_id, token=access_token)
#model = AutoModelForCausalLM.from_pretrained(model_id, token=access_token, load_in_4bit=True)
#model = AutoModelForCausalLM.from_pretrained(model_id, token=access_token)
# Initialize the quantizer
#quantizer = bnb.GemmQuantizer(act_bits=8, weight_bits=8)

# Quantize the model
#model = quantizer(model)

# Function to generate text using the model
def generate_text(prompt):
    text = prompt
    inputs = tokenizer(text, return_tensors="pt")
    
    outputs = model.generate(**inputs, max_new_tokens=20)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Create the Gradio interface
iface = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.inputs.Textbox(lines=5, label="Input Prompt"),
    ],
    outputs=gr.outputs.Textbox(label="Generated Text"),
    title="MisTRAL Text Generation",
    description="Use this interface to generate text using the MisTRAL language model.",
)

# Launch the Gradio interface
iface.launch()