File size: 1,104 Bytes
3643b73 95b2a11 dc09589 db46f1f d591ad9 3643b73 db46f1f 0b7787a 42db216 a1b3c51 0b7787a d591ad9 95b2a11 a3606dd d591ad9 dc09589 d591ad9 da2c202 dc09589 d591ad9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 |
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")
# 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() |