You can deploy this model and start earning money today!

BK-Lee/
CoLLaVO-7B

Name: CoLLaVO-7B
Availability: InStock

Views

No views yet

CoLLaVO model

This repository contains the weights of the model presented in CoLLaVO: Crayon Large Language and Vision mOdel.

Simple running code is based on MoAI-Github.

You need only the following seven steps.

Simple running code is based on CoLLaVO-Github.

You need only the following seven steps.

[0] Download Github Code of CoLLaVO, install the required libraries, set the necessary environment variable (README.md explains in detail! Don't Worry!).

bash

git clone https://github.com/ByungKwanLee/CoLLaVO
bash install

[1] Loading Image

python

from PIL import Image
from torchvision.transforms import Resize
from torchvision.transforms.functional import pil_to_tensor
image_path = "figures/crayon_image.jpg"
image = Resize(size=(490, 490), antialias=False)(pil_to_tensor(Image.open(image_path)))

[2] Instruction Prompt

prompt = "Describe this image in detail."

[3] Loading CoLlaVO

python

from collavo.load_collavo import prepare_collavo
collavo_model, collavo_processor, seg_model, seg_processor = prepare_collavo(collavo_path='BK-Lee/CoLLaVO-7B', bits=4, dtype='fp16')

[4] Pre-processing for CoLLaVO

python

collavo_inputs = collavo_model.demo_process(image=image, 
                                    prompt=prompt, 
                                    processor=collavo_processor,
                                    seg_model=seg_model,
                                    seg_processor=seg_processor,
                                    device='cuda:0')

[5] Generate

python

import torch
with torch.inference_mode():
    generate_ids = collavo_model.generate(**collavo_inputs, do_sample=True, temperature=0.9, top_p=0.95, max_new_tokens=256, use_cache=True)

[6] Decoding

python

answer = collavo_processor.batch_decode(generate_ids, skip_special_tokens=True)[0].split('[U')[0]
print(answer)