72 lines
3.1 KiB
Markdown
72 lines
3.1 KiB
Markdown
---
|
|
tags:
|
|
- Mantis
|
|
- VLM
|
|
- LMM
|
|
- Multimodal LLM
|
|
- llava
|
|
base_model: llava-hf/llava-1.5-7b-hf
|
|
model-index:
|
|
- name: Mantis-llava-7b
|
|
results: []
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
---
|
|
|
|
# Mantis: Interleaved Multi-Image Instruction Tuning (Deprecated)
|
|
|
|
**Mantis** is a multimodal conversational AI model that can chat with users about images and text. It's optimized for multi-image reasoning, where interleaved text and images can be used to generate responses.
|
|
|
|
**Note that this is an older version of Mantis**, please refer to our newest version at [mantis-Siglip-llama3](https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3). The newer version improves significantly over both multi-image and single-image tasks.
|
|
|
|
Mantis is trained on the newly curated dataset **Mantis-Instruct**, a large-scale multi-image QA dataset that covers various multi-image reasoning tasks.
|
|
|
|
|[Demo](https://huggingface.co/spaces/TIGER-Lab/Mantis) | [Github](https://github.com/TIGER-AI-Lab/Mantis) | [Models](https://huggingface.co/collections/TIGER-Lab/mantis-6619b0834594c878cdb1d6e4) |
|
|
|
|
|
|
|
|
## Inference
|
|
|
|
You can install Mantis's GitHub codes as a Python package
|
|
```bash
|
|
pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
|
|
```
|
|
then run inference with codes here: [examples/run_mantis.py](https://github.com/TIGER-AI-Lab/Mantis/blob/main/examples/run_mantis_hf.py)
|
|
|
|
```python
|
|
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.mllava import MLlavaProcessor, LlavaForConditionalGeneration
|
|
processor = MLlavaProcessor.from_pretrained("TIGER-Lab/Mantis-bakllava-7b")
|
|
model = LlavaForConditionalGeneration.from_pretrained("TIGER-Lab/Mantis-bakllava-7b", device_map="auto", torch_dtype=torch.bfloat16, attn_implementation="flash_attention_2")
|
|
|
|
# chat
|
|
text = "<image> <image> What's the difference between these two images? Please describe as much as you can."
|
|
response, history = chat_mllava(text, images, model, processor)
|
|
|
|
print("USER: ", text)
|
|
print("ASSISTANT: ", response)
|
|
# The image on the right has a larger number of wallets displayed compared to the image on the left. The wallets in the right image are arranged in a grid pattern, while the wallets in the left image are displayed in a more scattered manner. The wallets in the right image have various colors, including red, purple, and brown, while the wallets in the left image are primarily brown.
|
|
|
|
text = "How many items are there in image 1 and image 2 respectively?"
|
|
response, history = chat_mllava(text, images, model, processor, history=history)
|
|
|
|
print("USER: ", text)
|
|
print("ASSISTANT: ", response)
|
|
# There are two items in image 1 and four items in image 2.
|
|
```
|
|
|
|
Or, you can run the model without relying on the mantis codes, using pure hugging face transformers. See [examples/run_mantis_hf.py](https://github.com/TIGER-AI-Lab/Mantis/blob/main/examples/run_mantis_hf.py) for details.
|
|
|
|
|
|
## Training
|
|
Training codes will be released soon. |