News
See its paper: https://huggingface.co/papers/2402.16641
Load Model
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("q-future/co-instruct",
trust_remote_code=True,
torch_dtype=torch.float16,
attn_implementation="eager",
device_map={"":"cuda:0"})
Chat
import requests
from PIL import Image
prompt = "USER: The image: <|image|> Which happens in this image: motion-blur, over-exposure, or under-exposure? ASSISTANT:"
url = "https://raw.githubusercontent.com/Q-Future/Q-Align/main/fig/singapore_flyer.jpg"
image = Image.open(requests.get(url,stream=True).raw)
model.chat(prompt, [image], max_new_tokens=200)
prompt_cmp = "USER: The first image: <|image|>\nThe second image: <|image|>Which image has better quality, and why? ASSISTANT:"
url = "https://raw.githubusercontent.com/Q-Future/Q-Align/main/fig/boy_colorful.jpg"
image_2 = Image.open(requests.get(url,stream=True).raw)
model.chat(prompt_cmp, [image, image_2], max_new_tokens=200)