Total runs:
5.9M
Run Growth:
782.5K
Growth Rate:
13.29%
BAAI / Bunny-Llama-3-8B-V
Model's Last Updated: June 24 2024
text-generation
Introduction of Bunny-Llama-3-8B-V
Model Details of Bunny-Llama-3-8B-V
Model Card
📖 Technical report | 🏠 Code | 🐰 Demo | 🤗 GGUF
This is Bunny-Llama-3-8B-V.
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 Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM 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-Llama-3-8B-V, which is built upon SigLIP and Llama-3-8B-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-Llama-3-8B-V',
torch_dtype=torch.float16, # float32 for cpu
device_map='auto',
trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(
'BAAI/Bunny-Llama-3-8B-V',
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-Llama-3-8B-V on huggingface.co
272
Total runs
13
24-hour runs
23
3-day runs
72
7-day runs
-318
30-day runs
More Information About Bunny-Llama-3-8B-V huggingface.co Model
Url of Bunny-Llama-3-8B-V
Bunny-Llama-3-8B-V huggingface.co Url
Provider of Bunny-Llama-3-8B-V huggingface.co
Other API from BAAI
Updated: February 22 2024
Total runs:
2.3M
Run Growth:
-1.9M
Growth Rate:
-81.65%
Total runs:
1.6M
Run Growth:
-480.5K
Growth Rate:
-29.33%
Total runs:
1.1M
Run Growth:
-57.6K
Growth Rate:
-5.32%
Total runs:
996.4K
Run Growth:
283.2K
Growth Rate:
28.79%
Total runs:
798.5K
Run Growth:
157.2K
Growth Rate:
19.69%
Total runs:
783.1K
Run Growth:
-13.4K
Growth Rate:
-1.75%
Total runs:
196.1K
Run Growth:
22.0K
Growth Rate:
11.11%
Total runs:
138.3K
Run Growth:
71.2K
Growth Rate:
51.30%
Total runs:
124.5K
Run Growth:
-6.2K
Growth Rate:
-4.98%
Total runs:
25.5K
Run Growth:
-821
Growth Rate:
-3.18%
Total runs:
14.8K
Run Growth:
4.7K
Growth Rate:
31.52%
Total runs:
8.1K
Run Growth:
-11.1K
Growth Rate:
-84.72%
Total runs:
7.9K
Run Growth:
-1.3K
Growth Rate:
-16.23%
Total runs:
7.4K
Run Growth:
-1.6K
Growth Rate:
-21.40%
Total runs:
6.0K
Run Growth:
-1.4K
Growth Rate:
-23.31%
Total runs:
5.3K
Run Growth:
-1.8K
Growth Rate:
-32.62%
Total runs:
5.2K
Run Growth:
-1.9K
Growth Rate:
-35.09%
Total runs:
5.2K
Run Growth:
-1.9K
Growth Rate:
-35.11%
Total runs:
4.6K
Run Growth:
2.0K
Growth Rate:
44.08%
Total runs:
4.5K
Run Growth:
-10.8K
Growth Rate:
-268.38%
Total runs:
3.8K
Run Growth:
568
Growth Rate:
15.02%
Total runs:
3.5K
Run Growth:
-1.6K
Growth Rate:
-43.28%
Total runs:
3.5K
Run Growth:
-1.7K
Growth Rate:
-48.03%
Total runs:
2.6K
Run Growth:
196
Growth Rate:
7.14%
Total runs:
1.8K
Run Growth:
5
Growth Rate:
0.29%
Total runs:
1.2K
Run Growth:
922
Growth Rate:
78.67%
Total runs:
869
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:
533
Run Growth:
-633
Growth Rate:
-29.46%
Total runs:
425
Run Growth:
82
Growth Rate:
19.20%
Total runs:
409
Run Growth:
-158
Growth Rate:
-38.35%
Total runs:
186
Run Growth:
32
Growth Rate:
16.93%
Total runs:
143
Run Growth:
-314
Growth Rate:
-216.55%
Total runs:
108
Run Growth:
82
Growth Rate:
75.93%
Total runs:
107
Run Growth:
-95
Growth Rate:
-150.79%
Total runs:
70
Run Growth:
11
Growth Rate:
17.74%
Total runs:
40
Run Growth:
3
Growth Rate:
100.00%
Total runs:
40
Run Growth:
-10.2K
Growth Rate:
-21693.62%
Total runs:
39
Run Growth:
3
Growth Rate:
100.00%
Total runs:
23
Run Growth:
-41
Growth Rate:
-164.00%
Total runs:
23
Run Growth:
-440
Growth Rate:
-427.18%
Total runs:
21
Run Growth:
1
Growth Rate:
100.00%
Total runs:
18
Run Growth:
-27
Growth Rate:
-168.75%