OpenGVLab/InternVL-Chat-V1-2-Plus

Model Card for InternVL-Chat-V1.2-Plus

[InternVL 1.5 Technical Report] [Paper] [GitHub] [Chat Demo] [中文解读]

InternVL-Chat-V1.2-Plus uses the same model architecture as InternVL-Chat-V1.2, but the difference lies in the SFT dataset. InternVL-Chat-V1.2 only utilizes an SFT dataset with 1.2M samples, while our plus version employs an SFT dataset with 12M samples.

Model Details

• Model Type: multimodal large language model (MLLM)

• Model Stats:

  • Architecture: InternViT-6B-448px-V1-2 + MLP + Nous-Hermes-2-Yi-34B
  • Image size: 448 x 448 (256 tokens)
  • Params: 40B

• Training Strategy:

  • Pretraining Stage
    • Learnable Component: MLP
    • Data: Trained on 8192x4800=39.3M samples, including COYO, LAION, CC12M, CC3M, SBU, Wukong, GRIT, Objects365, OpenImages, and OCR data.
    • Note: In this stage, we load the pretrained weights of InternViT-6B-448px-V1-2. Moreover, in order to reduce the number of visual tokens, we use a pixel shuffle to reduce 1024 tokens to 256 tokens.
  • Supervised Finetuning Stage
    • Learnable Component: ViT + MLP + LLM
    • Data: 12 million SFT samples.

Released Models

Model	Vision Foundation Model	Release Date	Note
InternVL-Chat-V1.5(🤗 HF link)	InternViT-6B-448px-V1-5(🤗 HF link)	2024.04.18	support 4K image; super strong OCR; Approaching the performance of GPT-4V and Gemini Pro on various benchmarks like MMMU, DocVQA, ChartQA, MathVista, etc. (🔥new)
InternVL-Chat-V1.2-Plus(🤗 HF link )	InternViT-6B-448px-V1-2(🤗 HF link)	2024.02.21	more SFT data and stronger
InternVL-Chat-V1.2(🤗 HF link )	InternViT-6B-448px-V1-2(🤗 HF link)	2024.02.11	scaling up LLM to 34B
InternVL-Chat-V1.1(🤗 HF link)	InternViT-6B-448px-V1-0(🤗 HF link)	2024.01.24	support Chinese and stronger OCR

Performance

* Proprietary Model      † Training Set Observed

name	image size	MMMU (val)	MMMU (test)	MathVista (testmini)	MMB (test)	MMB−CN (test)	MMVP	MME	ScienceQA (image)	POPE	TextVQA (val)	SEEDv1 (image)	VizWiz (test)	GQA (test)
GPT-4V*	unknown	56.8	55.7	49.9	77.0	74.4	38.7	1409/517	-	-	78.0	71.6	-	-
Gemini Ultra*	unknown	59.4	-	53.0	-	-	-	-	-	-	82.3	-	-	-
Gemini Pro*	unknown	47.9	-	45.2	73.6	74.3	40.7	1497/437	-	-	74.6	70.7	-	-
Qwen−VL−Plus*	unknown	45.2	40.8	43.3	67.0	70.7	-	1681/502	-	-	78.9	65.7	-	-
Qwen−VL−Max*	unknown	51.4	46.8	51.0	77.6	75.7	-	-	-	-	79.5	-	-	-
LLaVA−NEXT−34B	672x672	51.1	44.7	46.5	79.3	79.0	-	1631/397	81.8	87.7	69.5	75.9	63.8	67.1†
InternVL−Chat−V1.2	448x448	51.6	46.2	47.7	82.2	81.2	56.7	1687/489	83.3	88.0	72.5	75.6	60.0	64.0†
InternVL−Chat−V1.2−Plus	448x448	50.3	45.6	59.9	83.8	82.0	58.7	1625/553	98.1†	88.7	74.1†	76.4	-	66.9†

• MMBench results are collected from the leaderboard.
• Update (2024-04-21): We have fixed a bug in the evaluation code, and the TextVQA results have been corrected.

Model Usage

We provide an example code to run InternVL-Chat-V1.2-Plus using transformers.

You also can use our online demo for a quick experience of this model.

import torch
from PIL import Image
from transformers import AutoModel, CLIPImageProcessor
from transformers import AutoTokenizer

path = "OpenGVLab/InternVL-Chat-V1-2-Plus"
# If you have an 80G A100 GPU, you can put the entire model on a single GPU.
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True).eval().cuda()
# Otherwise, you need to set device_map='auto' to use multiple GPUs for inference.
# model = AutoModel.from_pretrained(
#     path,
#     torch_dtype=torch.bfloat16,
#     low_cpu_mem_usage=True,
#     trust_remote_code=True,
#     device_map='auto').eval()

tokenizer = AutoTokenizer.from_pretrained(path)
image = Image.open('./examples/image2.jpg').convert('RGB')
image = image.resize((448, 448))
image_processor = CLIPImageProcessor.from_pretrained(path)

pixel_values = image_processor(images=image, return_tensors='pt').pixel_values
pixel_values = pixel_values.to(torch.bfloat16).cuda()

generation_config = dict(
    num_beams=1,
    max_new_tokens=512,
    do_sample=False,
)

# single-round conversation
question = "请详细描述图片"
response = model.chat(tokenizer, pixel_values, question, generation_config)
print(question, response)

# multi-round conversation
question = "请详细描述图片"
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
print(question, response)

question = "请根据图片写一首诗"
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
print(question, response)

Citation

If you find this project useful in your research, please consider citing:

@article{chen2023internvl,
  title={InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks},
  author={Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and Li, Bin and Luo, Ping and Lu, Tong and Qiao, Yu and Dai, Jifeng},
  journal={arXiv preprint arXiv:2312.14238},
  year={2023}
}

License

This project is released under the MIT license. Parts of this project contain code and models (e.g., LLaMA2) from other sources, which are subject to their respective licenses.

Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.

Acknowledgement

InternVL is built with reference to the code of the following projects: OpenAI CLIP, Open CLIP, CLIP Benchmark, EVA, InternImage, ViT-Adapter, MMSegmentation, Transformers, DINOv2, BLIP-2, Qwen-VL, and LLaVA-1.5. Thanks for their awesome work!