TIGER-Lab / Mantis-8B-Fuyu

huggingface.co
Total runs: 39
24-hour runs: 0
7-day runs: -4
30-day runs: 26
Model's Last Updated: May 04 2024
text-generation

Introduction of Mantis-8B-Fuyu

Model Details of Mantis-8B-Fuyu

🔥 Mantis

Paper | Website | Github | Models | Demo

Mantis

Summary
  • Mantis-Fuyu is a Fuyu based LMM with interleaved text and image as inputs , train on Mantis-Instruct under academic-level resources (i.e. 36 hours on 16xA100-40G).
  • Mantis is trained to have multi-image skills including co-reference, reasoning, comparing, temporal understanding.
  • Mantis reaches the state-of-the-art performance on five multi-image benchmarks (NLVR2, Q-Bench, BLINK, MVBench, Mantis-Eval), and also maintain a strong single-image performance on par with CogVLM and Emu2.
Multi-Image Performance

SoTA performance on 5 multi-image benchmarks

Single-Image Performance

Strong performance on single image results

How to use
Installation
# This only installs minimum packages (torch, transformers, accelerate) for inference, no redundant packages are installed.
pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
Run example inference:
from mantis.models.mllava import chat_mllava
from PIL import Image
import torch


image1 = "image1.jpg"
image2 = "image2.jpg"
images = [Image.open(image1), Image.open(image2)]

# load processor and model
from mantis.models.mfuyu import MFuyuForCausalLM, MFuyuProcessor
processor = MFuyuProcessor.from_pretrained("TIGER-Lab/Mantis-8B-Fuyu")
attn_implementation = None # or "flash_attention_2"
model = MFuyuForCausalLM.from_pretrained("TIGER-Lab/Mantis-8B-Fuyu", device_map="cuda", torch_dtype=torch.bfloat16, attn_implementation=attn_implementation)

generation_kwargs = {
    "max_new_tokens": 1024,
    "num_beams": 1,
    "do_sample": False,
    "pad_token_id": processor.tokenizer.eos_token_id,
}

# chat
text = "Describe the difference of <image> and <image> as much as you can."
response, history = chat_mllava(text, images, model, processor, **generation_kwargs)

print("USER: ", text)
print("ASSISTANT: ", response)

text = "How many wallets are there in image 1 and image 2 respectively?"
response, history = chat_mllava(text, images, model, processor, history=history, **generation_kwargs)

print("USER: ", text)
print("ASSISTANT: ", response)

"""
USER:  Describe the difference of <image> and <image> as much as you can.
ASSISTANT:  The second image has more variety in terms of colors and designs. While the first image only shows two brown leather pouches, the second image features four different pouches in various colors and designs, including a purple one with a gold coin, a red one with a gold coin, a black one with a gold coin, and a brown one with a gold coin. This variety makes the second image more visually interesting and dynamic.
USER:  How many wallets are there in image 1 and image 2 respectively?
ASSISTANT:  There are two wallets in image 1, and four wallets in image 2.
"""
Training

See mantis/train for details

Evaluation

See mantis/benchmark for details

Citation
@inproceedings{Jiang2024MANTISIM,
  title={MANTIS: Interleaved Multi-Image Instruction Tuning},
  author={Dongfu Jiang and Xuan He and Huaye Zeng and Cong Wei and Max W.F. Ku and Qian Liu and Wenhu Chen},
  publisher={arXiv2405.01483}
  year={2024},
}

Runs of TIGER-Lab Mantis-8B-Fuyu on huggingface.co

39
Total runs
0
24-hour runs
-6
3-day runs
-4
7-day runs
26
30-day runs

More Information About Mantis-8B-Fuyu huggingface.co Model

More Mantis-8B-Fuyu license Visit here:

https://choosealicense.com/licenses/cc-by-nc-4.0

Mantis-8B-Fuyu huggingface.co

Mantis-8B-Fuyu huggingface.co is an AI model on huggingface.co that provides Mantis-8B-Fuyu's model effect (), which can be used instantly with this TIGER-Lab Mantis-8B-Fuyu model. huggingface.co supports a free trial of the Mantis-8B-Fuyu model, and also provides paid use of the Mantis-8B-Fuyu. Support call Mantis-8B-Fuyu model through api, including Node.js, Python, http.

Mantis-8B-Fuyu huggingface.co Url

https://huggingface.co/TIGER-Lab/Mantis-8B-Fuyu

TIGER-Lab Mantis-8B-Fuyu online free

Mantis-8B-Fuyu huggingface.co is an online trial and call api platform, which integrates Mantis-8B-Fuyu's modeling effects, including api services, and provides a free online trial of Mantis-8B-Fuyu, you can try Mantis-8B-Fuyu online for free by clicking the link below.

TIGER-Lab Mantis-8B-Fuyu online free url in huggingface.co:

https://huggingface.co/TIGER-Lab/Mantis-8B-Fuyu

Mantis-8B-Fuyu install

Mantis-8B-Fuyu is an open source model from GitHub that offers a free installation service, and any user can find Mantis-8B-Fuyu on GitHub to install. At the same time, huggingface.co provides the effect of Mantis-8B-Fuyu install, users can directly use Mantis-8B-Fuyu installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Mantis-8B-Fuyu install url in huggingface.co:

https://huggingface.co/TIGER-Lab/Mantis-8B-Fuyu

Url of Mantis-8B-Fuyu

Mantis-8B-Fuyu huggingface.co Url

Provider of Mantis-8B-Fuyu huggingface.co

TIGER-Lab
ORGANIZATIONS

Other API from TIGER-Lab

huggingface.co

Total runs: 2.9K
Run Growth: 2.5K
Growth Rate: 86.16%
Updated:October 14 2025
huggingface.co

Total runs: 925
Run Growth: 320
Growth Rate: 34.59%
Updated:December 06 2023
huggingface.co

Total runs: 877
Run Growth: 323
Growth Rate: 36.83%
Updated:December 06 2023
huggingface.co

Total runs: 520
Run Growth: 462
Growth Rate: 88.85%
Updated:January 09 2025
huggingface.co

Total runs: 127
Run Growth: -344
Growth Rate: -270.87%
Updated:July 15 2026
huggingface.co

Total runs: 125
Run Growth: -346
Growth Rate: -276.80%
Updated:July 15 2026
huggingface.co

Total runs: 72
Run Growth: -361
Growth Rate: -501.39%
Updated:July 15 2026
huggingface.co

Total runs: 47
Run Growth: -389
Growth Rate: -827.66%
Updated:July 15 2026
huggingface.co

Total runs: 46
Run Growth: -399
Growth Rate: -867.39%
Updated:July 15 2026
huggingface.co

Total runs: 19
Run Growth: -14
Growth Rate: -73.68%
Updated:November 08 2024