Total runs:
5.8M
Run Growth:
1.5M
Growth Rate:
26.47%
BAAI / Bunny-v1_0-4B
Model's Last Updated: June 24 2024
text-generation
Introduction of Bunny-v1_0-4B
Model Details of Bunny-v1_0-4B
Model Card
📖 Technical report | 🏠 Code | 🐰 Demo | 🤗 GGUF
This is Bunny-v1.0-4B.
We also provide v1.1 version accepting high-resolution images up to 1152x1152. 🤗 v1.1
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-v1.0-4B, which is built upon SigLIP and Phi-3-Mini-4K-Instruct . 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_0-4B',
torch_dtype=torch.float16, # float32 for cpu
device_map='auto',
trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(
'BAAI/Bunny-v1_0-4B',
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_0-4B on huggingface.co
34
Total runs
-5
24-hour runs
-3
3-day runs
-2
7-day runs
-227
30-day runs
More Information About Bunny-v1_0-4B huggingface.co Model
Url of Bunny-v1_0-4B
Bunny-v1_0-4B huggingface.co Url
Provider of Bunny-v1_0-4B huggingface.co
Other API from BAAI
Updated: February 22 2024
Total runs:
2.2M
Run Growth:
-2.3M
Growth Rate:
-114.09%
Total runs:
1.6M
Run Growth:
-138.6K
Growth Rate:
-8.70%
Total runs:
1.2M
Run Growth:
594.9K
Growth Rate:
49.93%
Total runs:
990.8K
Run Growth:
-6.1K
Growth Rate:
-0.60%
Total runs:
967.6K
Run Growth:
293.1K
Growth Rate:
30.63%
Total runs:
954.2K
Run Growth:
640.3K
Growth Rate:
65.68%
Total runs:
759.4K
Run Growth:
148.9K
Growth Rate:
19.54%
Total runs:
152.3K
Run Growth:
-20.8K
Growth Rate:
-13.29%
Total runs:
139.5K
Run Growth:
45.3K
Growth Rate:
32.49%
Total runs:
131.4K
Run Growth:
12.7K
Growth Rate:
9.57%
Total runs:
25.6K
Run Growth:
-622
Growth Rate:
-2.59%
Total runs:
13.2K
Run Growth:
4.2K
Growth Rate:
31.91%
Total runs:
7.5K
Run Growth:
-421
Growth Rate:
-5.62%
Total runs:
7.1K
Run Growth:
-11.1K
Growth Rate:
-84.72%
Total runs:
6.8K
Run Growth:
-3.2K
Growth Rate:
-50.67%
Total runs:
6.5K
Run Growth:
44
Growth Rate:
0.68%
Total runs:
5.5K
Run Growth:
-1.3K
Growth Rate:
-25.42%
Total runs:
5.4K
Run Growth:
-920
Growth Rate:
-17.16%
Total runs:
5.3K
Run Growth:
-814
Growth Rate:
-15.40%
Total runs:
5.3K
Run Growth:
-831
Growth Rate:
-15.70%
Total runs:
5.0K
Run Growth:
2.6K
Growth Rate:
50.81%
Total runs:
4.3K
Run Growth:
1.3K
Growth Rate:
31.16%
Total runs:
3.8K
Run Growth:
-501
Growth Rate:
-13.45%
Total runs:
3.7K
Run Growth:
-610
Growth Rate:
-16.58%
Total runs:
2.8K
Run Growth:
196
Growth Rate:
7.14%
Total runs:
2.1K
Run Growth:
1.0K
Growth Rate:
51.10%
Total runs:
1.3K
Run Growth:
1.1K
Growth Rate:
88.27%
Total runs:
1.2K
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:
476
Run Growth:
-633
Growth Rate:
-29.46%
Total runs:
355
Run Growth:
-1
Growth Rate:
-0.29%
Total runs:
310
Run Growth:
-177
Growth Rate:
-54.80%
Total runs:
201
Run Growth:
68
Growth Rate:
32.85%
Total runs:
133
Run Growth:
-180
Growth Rate:
-136.36%
Total runs:
97
Run Growth:
70
Growth Rate:
70.71%
Total runs:
64
Run Growth:
-95
Growth Rate:
-150.79%
Total runs:
53
Run Growth:
11
Growth Rate:
17.74%
Total runs:
41
Run Growth:
3
Growth Rate:
100.00%
Total runs:
28
Run Growth:
-440
Growth Rate:
-427.18%
Total runs:
27
Run Growth:
-4.2K
Growth Rate:
-16792.00%
Total runs:
24
Run Growth:
1
Growth Rate:
100.00%
Total runs:
24
Run Growth:
3
Growth Rate:
100.00%
Total runs:
19
Run Growth:
-17
Growth Rate:
-89.47%