Total runs:
6.0M
Run Growth:
812.1K
Growth Rate:
13.68%
BAAI / Bunny-v1_1-4B
Model's Last Updated: June 24 2024
text-generation
Introduction of Bunny-v1_1-4B
Model Details of Bunny-v1_1-4B
Model Card
📖 Technical report | 🏠 Code | 🐰 Demo
This is Bunny-v1.1-4B.
Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Phi-3-mini, Llama-3-8B, Phi-1.5, StableLM-2 and Phi-2. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.
We provide Bunny-v1.1-4B, which is built upon SigLIP and Phi-3-mini-4k-instruct with S -Wrapper , supporting 1152x1152 resolution. More details about this model can be found in GitHub .
Quickstart
Here we show a code snippet to show you how to use the model with transformers.
Before running the snippet, you need to install the following dependencies:
pip install torch transformers accelerate pillow
If the CUDA memory is enough, it would be faster to execute this snippet by setting
CUDA_VISIBLE_DEVICES=0
.
Users especially those in Chinese mainland may want to refer to a HuggingFace mirror site .
import torch
import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image
import warnings
# disable some warnings
transformers.logging.set_verbosity_error()
transformers.logging.disable_progress_bar()
warnings.filterwarnings('ignore')
# set device
device = 'cuda' # or cpu
torch.set_default_device(device)
# create model
model = AutoModelForCausalLM.from_pretrained(
'BAAI/Bunny-v1_1-4B',
torch_dtype=torch.float16, # float32 for cpu
device_map='auto',
trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(
'BAAI/Bunny-v1_1-4B',
trust_remote_code=True)
# text prompt
prompt = 'Why is the image funny?'
text = f"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\n{prompt} ASSISTANT:"
text_chunks = [tokenizer(chunk).input_ids for chunk in text.split('<image>')]
input_ids = torch.tensor(text_chunks[0] + [-200] + text_chunks[1][1:], dtype=torch.long).unsqueeze(0).to(device)
# image, sample images can be found in images folder
image = Image.open('example_2.png')
image_tensor = model.process_images([image], model.config).to(dtype=model.dtype, device=device)
# generate
output_ids = model.generate(
input_ids,
images=image_tensor,
max_new_tokens=100,
use_cache=True,
repetition_penalty=1.0 # increase this to avoid chattering
)[0]
print(tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip())
Runs of BAAI Bunny-v1_1-4B on huggingface.co
52
Total runs
21
24-hour runs
15
3-day runs
-40
7-day runs
-243
30-day runs
More Information About Bunny-v1_1-4B huggingface.co Model
Url of Bunny-v1_1-4B
Bunny-v1_1-4B huggingface.co Url
Provider of Bunny-v1_1-4B huggingface.co
Other API from BAAI
Updated: February 22 2024
Total runs:
2.2M
Run Growth:
-2.0M
Growth Rate:
-90.33%
Total runs:
1.6M
Run Growth:
-464.9K
Growth Rate:
-28.46%
Total runs:
1.1M
Run Growth:
128.8K
Growth Rate:
11.79%
Total runs:
1.0M
Run Growth:
-101.9K
Growth Rate:
-9.65%
Total runs:
1.0M
Run Growth:
368.4K
Growth Rate:
36.98%
Total runs:
789.6K
Run Growth:
-5.5K
Growth Rate:
-0.70%
Total runs:
781.8K
Run Growth:
150.9K
Growth Rate:
18.90%
Total runs:
192.5K
Run Growth:
19.9K
Growth Rate:
10.13%
Total runs:
137.3K
Run Growth:
67.1K
Growth Rate:
48.53%
Total runs:
126.6K
Run Growth:
-7.2K
Growth Rate:
-5.80%
Total runs:
24.9K
Run Growth:
-1.4K
Growth Rate:
-5.38%
Total runs:
14.3K
Run Growth:
4.7K
Growth Rate:
31.84%
Total runs:
8.0K
Run Growth:
-11.1K
Growth Rate:
-84.72%
Total runs:
7.7K
Run Growth:
-2.0K
Growth Rate:
-24.86%
Total runs:
7.3K
Run Growth:
-1.7K
Growth Rate:
-23.46%
Total runs:
6.0K
Run Growth:
-1.5K
Growth Rate:
-24.26%
Total runs:
5.2K
Run Growth:
-1.9K
Growth Rate:
-36.11%
Total runs:
5.2K
Run Growth:
-2.0K
Growth Rate:
-37.47%
Total runs:
5.1K
Run Growth:
-1.9K
Growth Rate:
-37.42%
Total runs:
4.7K
Run Growth:
2.1K
Growth Rate:
45.11%
Total runs:
4.5K
Run Growth:
-9.5K
Growth Rate:
-214.25%
Total runs:
3.9K
Run Growth:
625
Growth Rate:
16.33%
Total runs:
3.5K
Run Growth:
-1.6K
Growth Rate:
-46.07%
Total runs:
3.4K
Run Growth:
-1.8K
Growth Rate:
-50.90%
Total runs:
2.6K
Run Growth:
196
Growth Rate:
7.14%
Total runs:
1.8K
Run Growth:
-7
Growth Rate:
-0.40%
Total runs:
1.2K
Run Growth:
926
Growth Rate:
78.88%
Total runs:
827
Run Growth:
25
Growth Rate:
86.21%
Total runs:
664
Run Growth:
0
Growth Rate:
0.00%
Total runs:
644
Run Growth:
0
Growth Rate:
0.00%
Total runs:
530
Run Growth:
-633
Growth Rate:
-29.46%
Total runs:
414
Run Growth:
77
Growth Rate:
18.12%
Total runs:
374
Run Growth:
-159
Growth Rate:
-38.88%
Total runs:
274
Run Growth:
-340
Growth Rate:
-125.00%
Total runs:
185
Run Growth:
29
Growth Rate:
15.59%
Total runs:
142
Run Growth:
-283
Growth Rate:
-197.90%
Total runs:
108
Run Growth:
80
Growth Rate:
74.07%
Total runs:
107
Run Growth:
-95
Growth Rate:
-150.79%
Total runs:
66
Run Growth:
11
Growth Rate:
17.74%
Total runs:
40
Run Growth:
3
Growth Rate:
100.00%
Total runs:
37
Run Growth:
3
Growth Rate:
100.00%
Total runs:
36
Run Growth:
-10.2K
Growth Rate:
-25530.00%
Total runs:
25
Run Growth:
-46
Growth Rate:
-200.00%
Total runs:
24
Run Growth:
-440
Growth Rate:
-427.18%
Total runs:
21
Run Growth:
1
Growth Rate:
100.00%
Total runs:
18
Run Growth:
-25
Growth Rate:
-138.89%