File size: 1,108 Bytes
4bc1572 1838b80 4bc1572 1838b80 fec45e6 4bc1572 fec45e6 4bc1572 fec45e6 4bc1572 fec45e6 4bc1572 fec45e6 4bc1572 fec45e6 4bc1572 |
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 36 37 38 39 |
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image
import gradio as gr
model = AutoModelForCausalLM.from_pretrained(
"MILVLG/imp-v1-3b",
torch_dtype=torch.float16,
device_map="auto",
trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("MILVLG/imp-v1-3b", trust_remote_code=True)
def generate_answer(text, image):
input_ids = tokenizer(text, return_tensors='pt').input_ids
image_tensor = model.image_preprocess(image)
output_ids = model.generate(
input_ids,
max_new_tokens=100,
images=image_tensor,
use_cache=True)[0]
return tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()
text_input = gr.Textbox(lines=5, label="Enter text")
image_input = gr.Image(shape=(224, 224), label="Upload Image")
iface = gr.Interface(
fn=generate_answer,
inputs=[text_input, image_input],
outputs="text",
title="DD360-Bot-Multimodal",
description="Enter text and upload an image to receive a response from the chatbot."
)
iface.launch()
|