Total runs:
63.1M
Run Growth:
-3.2M
Growth Rate:
-5.07%
Sponsored by
iMean AI Trip Planner
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
191
Total runs
-3
24-hour runs
11
3-day runs
26
7-day runs
48
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:
17.1M
Run Growth:
-710.4K
Growth Rate:
-4.15%
Total runs:
10.2M
Run Growth:
-1.2M
Growth Rate:
-12.18%
Total runs:
9.8M
Run Growth:
-3.5M
Growth Rate:
-36.13%
Total runs:
4.7M
Run Growth:
-43.0K
Growth Rate:
-0.92%
Total runs:
2.4M
Run Growth:
-127.8K
Growth Rate:
-5.25%
Total runs:
734.0K
Run Growth:
-391.2K
Growth Rate:
-53.30%
Total runs:
639.8K
Run Growth:
-390.0K
Growth Rate:
-60.97%
Total runs:
327.1K
Run Growth:
64.9K
Growth Rate:
19.84%
Total runs:
200.3K
Run Growth:
-476.2K
Growth Rate:
-237.76%
Total runs:
162.0K
Run Growth:
3.4K
Growth Rate:
2.12%
Total runs:
82.5K
Run Growth:
-228.7K
Growth Rate:
-277.48%
Total runs:
58.6K
Run Growth:
-10.0K
Growth Rate:
-17.12%
Total runs:
16.6K
Run Growth:
531
Growth Rate:
3.20%
Total runs:
10.4K
Run Growth:
10.4K
Growth Rate:
100.00%
Total runs:
8.7K
Run Growth:
406
Growth Rate:
4.66%
Total runs:
8.7K
Run Growth:
455
Growth Rate:
5.23%
Total runs:
2.5K
Run Growth:
-4.0K
Growth Rate:
-159.22%
Total runs:
2.3K
Run Growth:
974
Growth Rate:
42.02%
Total runs:
2.3K
Run Growth:
253
Growth Rate:
11.07%
Total runs:
1.2K
Run Growth:
270
Growth Rate:
23.18%
Total runs:
830
Run Growth:
407
Growth Rate:
49.04%
Total runs:
771
Run Growth:
141
Growth Rate:
18.29%
Total runs:
736
Run Growth:
736
Growth Rate:
100.00%
Total runs:
664
Run Growth:
0
Growth Rate:
0.00%
Total runs:
644
Run Growth:
0
Growth Rate:
0.00%
Total runs:
461
Run Growth:
-159
Growth Rate:
-34.49%
Total runs:
317
Run Growth:
-437
Growth Rate:
-137.85%
Total runs:
232
Run Growth:
95
Growth Rate:
41.85%
Total runs:
204
Run Growth:
92
Growth Rate:
45.10%
Total runs:
196
Run Growth:
-2.0K
Growth Rate:
-1035.20%
Total runs:
193
Run Growth:
43
Growth Rate:
22.28%
Total runs:
186
Run Growth:
60
Growth Rate:
32.61%
Total runs:
182
Run Growth:
57
Growth Rate:
31.32%