Ovis1.6-Llama3.2-3B
Introduction
We are thrilled to announce the open-sourcing of Ovis1.6-Llama3.2-3B, an integral part of the Ovis1.6 family. This cutting-edge model currently sets the benchmark as the state-of-the-art (SOTA) solution for edge-side multimodal tasks.
The Ovis family employs an innovative Multimodal Large Language Model (MLLM) architecture, specifically designed to structurally align visual and textual embeddings. Ovis1.6-Llama3.2-3B excels in common industry benchmarks, surpassing numerous open-source and proprietary multimodal models. Moreover, it is also particularly well-suited for local intelligence, on-device computing, and edge computing scenarios.
Model
Built upon Ovis1.5, Ovis1.6 further enhances high-resolution image processing, is trained on a larger, more diverse, and higher-quality dataset, and refines the training process with DPO training following instruction-tuning.
| Ovis MLLMs | ViT | LLM | Model Weights | Demo |
|---|---|---|---|---|
| Ovis1.6-Gemma2-9B | Siglip-400M | Gemma2-9B-It | Huggingface | Space |
| Ovis1.6-Llama3.2-3B | Siglip-400M | Llama-3.2-3B-Instruct | Huggingface | Space |
Performance
Ovis1.6-Llama3.2-3B leads the OpenCompass benchmark among open-source MLLMs under 4B parameters, even surpassing Llama-3.2-11B-Vision-Instruct.
Usage
Below is a code snippet to run Ovis with multimodal inputs. For additional usage instructions, including inference wrapper and Gradio UI, please refer to Ovis GitHub.
pip install torch==2.2.0 transformers==4.44.2 numpy==1.24.3 pillow==10.3.0
pip install flash-attn --no-build-isolation
import torch
from PIL import Image
from transformers import AutoModelForCausalLM
# load model
model = AutoModelForCausalLM.from_pretrained("AIDC-AI/Ovis1.6-Llama3.2-3B",
torch_dtype=torch.bfloat16,
multimodal_max_length=8192,
trust_remote_code=True).cuda()
text_tokenizer = model.get_text_tokenizer()
visual_tokenizer = model.get_visual_tokenizer()
# enter image path and prompt
image_path = input("Enter image path: ")
image = Image.open(image_path)
text = input("Enter prompt: ")
query = f'<image>\n{text}'
# format conversation
prompt, input_ids, pixel_values = model.preprocess_inputs(query, [image])
attention_mask = torch.ne(input_ids, text_tokenizer.pad_token_id)
input_ids = input_ids.unsqueeze(0).to(device=model.device)
attention_mask = attention_mask.unsqueeze(0).to(device=model.device)
pixel_values = [pixel_values.to(dtype=visual_tokenizer.dtype, device=visual_tokenizer.device)]
# generate output
with torch.inference_mode():
gen_kwargs = dict(
max_new_tokens=1024,
do_sample=False,
top_p=None,
top_k=None,
temperature=None,
repetition_penalty=None,
eos_token_id=model.generation_config.eos_token_id,
pad_token_id=text_tokenizer.pad_token_id,
use_cache=True
)
output_ids = model.generate(input_ids, pixel_values=pixel_values, attention_mask=attention_mask, **gen_kwargs)[0]
output = text_tokenizer.decode(output_ids, skip_special_tokens=True)
print(f'Output:\n{output}')
Batch inference
batch_inputs = [
('example_image1.jpeg', 'Describe the content of this image.'),
('example_image2.jpeg', 'What is the equation in the image?')
]
batch_input_ids = []
batch_attention_mask = []
batch_pixel_values = []
for image_path, text in batch_inputs:
image = Image.open(image_path)
query = f'<image>\n{text}'
prompt, input_ids, pixel_values = model.preprocess_inputs(query, [image])
attention_mask = torch.ne(input_ids, text_tokenizer.pad_token_id)
input_ids = input_ids.unsqueeze(0).to(device=model.device)
attention_mask = attention_mask.unsqueeze(0).to(device=model.device)
pixel_values = [pixel_values.to(dtype=visual_tokenizer.dtype, device=visual_tokenizer.device)]
batch_input_ids.append(input_ids.squeeze())
batch_attention_mask.append(attention_mask.squeeze())
batch_pixel_values.append(pixel_values)
pad_batch_input_ids = torch.nn.utils.rnn.pad_sequence([i.flip(dims=[0]) for i in batch_input_ids],batch_first=True, padding_value=0.0).flip(dims=[1])
pad_batch_input_ids = pad_batch_input_ids[:,-model.config.multimodal_max_length:]
pad_batch_attention_mask = torch.nn.utils.rnn.pad_sequence([i.flip(dims=[0]) for i in batch_attention_mask],batch_first=True, padding_value=False).flip(dims=[1])
pad_batch_attention_mask = pad_batch_attention_mask[:,-model.config.multimodal_max_length:]
pad_batch_pixel_values = [item for sublist in batch_pixel_values for item in sublist]
# generate output
with torch.inference_mode():
gen_kwargs = dict(
max_new_tokens=1024,
do_sample=False,
top_p=None,
top_k=None,
temperature=None,
repetition_penalty=None,
eos_token_id=model.generation_config.eos_token_id,
pad_token_id=text_tokenizer.pad_token_id,
use_cache=True
)
output_ids = model.generate(pad_batch_input_ids, pixel_values=pad_batch_pixel_values, attention_mask=pad_batch_attention_mask, **gen_kwargs)
for i in range(len(batch_input_ids)):
output = text_tokenizer.decode(output_ids[i], skip_special_tokens=True)
print(f'Output_{i}:\n{output}')
Citation
If you find Ovis useful, please cite the paper
@article{lu2024ovis,
title={Ovis: Structural Embedding Alignment for Multimodal Large Language Model},
author={Shiyin Lu and Yang Li and Qing-Guo Chen and Zhao Xu and Weihua Luo and Kaifu Zhang and Han-Jia Ye},
year={2024},
journal={arXiv:2405.20797}
}
License
This project is licensed under the Apache License, Version 2.0 (SPDX-License-Identifier: Apache-2.0).
Disclaimer
We used compliance-checking algorithms during the training process, to ensure the compliance of the trained model to the best of our ability. Due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model is completely free of copyright issues or improper content. If you believe anything infringes on your rights or generates improper content, please contact us, and we will promptly address the matter.