File size: 2,000 Bytes
88d2311 9dd6788 88d2311 |
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 40 41 42 |
Use `transformers==4.36.1`. Preview version only.
This model has reached 75.99\% accuracy on Q-Bench A1 *test* (multi-choice questions), notably superior than GPT-4V (73.44\%).
### Load Model
```python
import torch
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("q-future/co-instruct-preview",
trust_remote_code=True,
torch_dtype=torch.float16,
attn_implementation="flash_attention_2",
device_map={"":"cuda:0"})
```
### Chat
```python
import requests
from PIL import Image
### Single 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)
## Motion blur
### Double Image Comparison
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)
## The second image has better quality. The description indicates that the image has accurate exposure, precise focus, clear details, rich colors, and sufficient lighting. Additionally, the texture details are clear, and the composition is centered. In comparison, the first image has good clarity and rich texture details, but the lighting is slightly weak, which can affect the overall quality of the image. Therefore, the second image is of higher quality due to its accurate exposure, precise focus, clear details, rich colors, sufficient lighting, and centered composition.
``` |