Hugging Face's logo

OpenGVLab
/
Mono-InternVL-2B

Image-Text-to-Text
Transformers
Safetensors
multilingual
internvl_chat
feature-extraction
internvl
vision
ocr
custom_code
Mixture of Experts
conversational
Model card Files Community
10
Mono-InternVL-2B / README.md
wzk1015's picture
wzk1015
Update README.md
d8210be verified
preview code
|
raw
history blame
35.1 kB
metadata
license: mit
pipeline_tag: image-text-to-text
library_name: transformers
base_model:
  - internlm/internlm2-chat-1_8b
base_model_relation: merge
language:
  - multilingual
tags:
  - internvl
  - vision
  - ocr
  - video
  - custom_code

Mono-InternVL-2B

[📂 GitHub] [📜 Mono-InternVL Paper]

切换至中文版

image/png

image/png

Introduction

We release Mono-InternVL, a monolithic multimodal large language model (MLLM) that integrates visual encoding and textual decoding into a single LLM. In Mono-InternVL, a set of visual experts is embedded into the pre-trained LLM via a mixture-of-experts mechanism. By freezing the LLM, Mono-InternVL ensures that visual capabilities are optimized without compromising the pre-trained language knowledge. Based on this structure, an innovative Endogenous Visual Pretraining (EViP) is introduced to realize coarse-to-fine visual learning.

Mono-InternVL achieves superior performance compared to state-of-the-art MLLM Mini-InternVL-2B-1.5 and significantly outperforms other monolithic MLLMs, as shown in the radar chart above. Meanwhile, it achieves better deployment efficiency, with first token latency reduced by up to 67%.

This repository contains the instruction-tuned Mono-InternVL-2B model. It is built upon internlm2-chat-1_8b. For more details, please refer to our paper.

Performance

Benchmark Chameleon-7B EVE-7B (HD) Emu3 Mini-InternVL-2B-1-5 Mono-InternVL-2B
Type Monolithic Monolithic Monolithic Modular Monolithic
#Activated Params 7B 7B 8B 2.2B 1.8B
MMVet 8.3 25.7 37.2 39.3 40.1
MMMUval 25.4 32.6 31.6 34.6 33.7
MMEsum 170 1628 — 1902 1875
MMBench-ENtest 31.1 52.3 58.5 70.9 65.5
MathVistatestmini 22.3 34.2 — 41.1 45.7
SEED-Image 30.6 64.6 68.2 69.8 67.4
OCRBench 7 398 687 654 767
Hallusion-Bench 17.1 26.4 — 37.5 34.8
CCBenchdev 3.5 16.3 — 63.5 66.3
Avgmultimodal 16.1 38.9 — 54.4 55.2
TextVQAval 4.8 56.8 64.7 70.5 72.6
SQA-Itest 47.2 64.9 89.2 84.9 93.6
GQAtest — 62.6 60.3 61.6 59.5
DocVQAtest 1.5 53.0 76.3 85.0 80.0
AI2Dtest 46.0 61.0 70.0 69.8 68.6
ChartQAtest 2.9 59.1 68.6 74.8 73.7
InfoVQAtest 5.0 25.0 43.8 55.4 43.0
AvgVQA 17.9 54.6 67.6 71.7 70.1
  • Sources of the results include the original papers, our evaluation with VLMEvalKit, and OpenCompass.
  • Average scores are computed by normalizing each metric to a range between 0 and 100.
  • Please note that evaluating the same model using different testing toolkits can result in slight differences, which is normal. Updates to code versions and variations in environment and hardware can also cause minor discrepancies in results.

Limitations: Although we have made efforts to ensure the safety of the model during the training process and to encourage the model to generate text that complies with ethical and legal requirements, the model may still produce unexpected outputs due to its size and probabilistic generation paradigm. For example, the generated responses may contain biases, discrimination, or other harmful content. Please do not propagate such content. We are not responsible for any consequences resulting from the dissemination of harmful information.

Quick Start

We provide an example code to run Mono-InternVL-2B using transformers.

Please use transformers==4.37.2TODO to ensure the model works normally.

Model Loading

16-bit (bf16 / fp16) 

import torch
from transformers import AutoTokenizer, AutoModel
path = "OpenGVLab/Mono-InternVL-2B"
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    use_flash_attn=True,
    trust_remote_code=True).eval().cuda()

BNB 8-bit Quantization 

import torch
from transformers import AutoTokenizer, AutoModel
path = "OpenGVLab/Mono-InternVL-2B"
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    load_in_8bit=True,
    low_cpu_mem_usage=True,
    use_flash_attn=True,
    trust_remote_code=True).eval()

BNB 4-bit Quantization 

import torch
from transformers import AutoTokenizer, AutoModel
path = "OpenGVLab/Mono-InternVL-2B"
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    load_in_4bit=True,
    low_cpu_mem_usage=True,
    use_flash_attn=True,
    trust_remote_code=True).eval()

Multiple GPUs

The reason for writing the code this way is to avoid errors that occur during multi-GPU inference due to tensors not being on the same device. By ensuring that the first and last layers of the large language model (LLM) are on the same device, we prevent such errors.

import math
import torch
from transformers import AutoTokenizer, AutoModel

def split_model(model_name):
    device_map = {}
    world_size = torch.cuda.device_count()
    num_layers = {'Mono-InternVL-2B': 24}[model_name]
    # Since the first GPU will be used for ViT, treat it as half a GPU.
    num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
    num_layers_per_gpu = [num_layers_per_gpu] * world_size
    num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
    layer_cnt = 0
    for i, num_layer in enumerate(num_layers_per_gpu):
        for j in range(num_layer):
            device_map[f'language_model.model.layers.{layer_cnt}'] = i
            layer_cnt += 1
    device_map['vision_model'] = 0
    device_map['mlp1'] = 0
    device_map['language_model.model.tok_embeddings'] = 0
    device_map['language_model.model.embed_tokens'] = 0
    device_map['language_model.output'] = 0
    device_map['language_model.model.norm'] = 0
    device_map['language_model.lm_head'] = 0
    device_map[f'language_model.model.layers.{num_layers - 1}'] = 0

    return device_map

path = "OpenGVLab/Mono-InternVL-2B"
device_map = split_model('Mono-InternVL-2B')
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    use_flash_attn=True,
    trust_remote_code=True,
    device_map=device_map).eval()

Inference with Transformers 

import numpy as np
import torch
import torchvision.transforms as T
from decord import VideoReader, cpu
from PIL import Image
from torchvision.transforms.functional import InterpolationMode
from transformers import AutoModel, AutoTokenizer

IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)

def build_transform(input_size):
    MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
    transform = T.Compose([
        T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
        T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
        T.ToTensor(),
        T.Normalize(mean=MEAN, std=STD)
    ])
    return transform

def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
    best_ratio_diff = float('inf')
    best_ratio = (1, 1)
    area = width * height
    for ratio in target_ratios:
        target_aspect_ratio = ratio[0] / ratio[1]
        ratio_diff = abs(aspect_ratio - target_aspect_ratio)
        if ratio_diff < best_ratio_diff:
            best_ratio_diff = ratio_diff
            best_ratio = ratio
        elif ratio_diff == best_ratio_diff:
            if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
                best_ratio = ratio
    return best_ratio

def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
    orig_width, orig_height = image.size
    aspect_ratio = orig_width / orig_height

    # calculate the existing image aspect ratio
    target_ratios = set(
        (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
        i * j <= max_num and i * j >= min_num)
    target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])

    # find the closest aspect ratio to the target
    target_aspect_ratio = find_closest_aspect_ratio(
        aspect_ratio, target_ratios, orig_width, orig_height, image_size)

    # calculate the target width and height
    target_width = image_size * target_aspect_ratio[0]
    target_height = image_size * target_aspect_ratio[1]
    blocks = target_aspect_ratio[0] * target_aspect_ratio[1]

    # resize the image
    resized_img = image.resize((target_width, target_height))
    processed_images = []
    for i in range(blocks):
        box = (
            (i % (target_width // image_size)) * image_size,
            (i // (target_width // image_size)) * image_size,
            ((i % (target_width // image_size)) + 1) * image_size,
            ((i // (target_width // image_size)) + 1) * image_size
        )
        # split the image
        split_img = resized_img.crop(box)
        processed_images.append(split_img)
    assert len(processed_images) == blocks
    if use_thumbnail and len(processed_images) != 1:
        thumbnail_img = image.resize((image_size, image_size))
        processed_images.append(thumbnail_img)
    return processed_images

def load_image(image_file, input_size=448, max_num=12):
    image = Image.open(image_file).convert('RGB')
    transform = build_transform(input_size=input_size)
    images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
    pixel_values = [transform(image) for image in images]
    pixel_values = torch.stack(pixel_values)
    return pixel_values

# If you want to load a model using multiple GPUs, please refer to the `Multiple GPUs` section.
path = 'OpenGVLab/Mono-InternVL-2B'
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    use_flash_attn=True,
    trust_remote_code=True).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)

# set the max number of tiles in `max_num`
pixel_values = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
generation_config = dict(max_new_tokens=1024, do_sample=True)

# pure-text conversation (纯文本对话)
question = 'Hello, who are you?'
response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'Can you tell me a story?'
response, history = model.chat(tokenizer, None, question, generation_config, history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')

# single-image single-round conversation (单图单轮对话)
question = '<image>\nPlease describe the image shortly.'
response = model.chat(tokenizer, pixel_values, question, generation_config)
print(f'User: {question}\nAssistant: {response}')

# single-image multi-round conversation (单图多轮对话)
question = '<image>\nPlease describe the image in detail.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'Please write a poem according to the image.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')

# multi-image multi-round conversation, combined images (多图多轮对话，拼接图像)
pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)

question = '<image>\nDescribe the two images in detail.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'What are the similarities and differences between these two images.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')

# multi-image multi-round conversation, separate images (多图多轮对话，独立图像)
pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]

question = 'Image-1: <image>\nImage-2: <image>\nDescribe the two images in detail.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list,
                               history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'What are the similarities and differences between these two images.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list,
                               history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')

# batch inference, single image per sample (单图批处理)
pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)

questions = ['<image>\nDescribe the image in detail.'] * len(num_patches_list)
responses = model.batch_chat(tokenizer, pixel_values,
                             num_patches_list=num_patches_list,
                             questions=questions,
                             generation_config=generation_config)
for question, response in zip(questions, responses):
    print(f'User: {question}\nAssistant: {response}')

# video multi-round conversation (视频多轮对话)
def get_index(bound, fps, max_frame, first_idx=0, num_segments=32):
    if bound:
        start, end = bound[0], bound[1]
    else:
        start, end = -100000, 100000
    start_idx = max(first_idx, round(start * fps))
    end_idx = min(round(end * fps), max_frame)
    seg_size = float(end_idx - start_idx) / num_segments
    frame_indices = np.array([
        int(start_idx + (seg_size / 2) + np.round(seg_size * idx))
        for idx in range(num_segments)
    ])
    return frame_indices

def load_video(video_path, bound=None, input_size=448, max_num=1, num_segments=32):
    vr = VideoReader(video_path, ctx=cpu(0), num_threads=1)
    max_frame = len(vr) - 1
    fps = float(vr.get_avg_fps())

    pixel_values_list, num_patches_list = [], []
    transform = build_transform(input_size=input_size)
    frame_indices = get_index(bound, fps, max_frame, first_idx=0, num_segments=num_segments)
    for frame_index in frame_indices:
        img = Image.fromarray(vr[frame_index].asnumpy()).convert('RGB')
        img = dynamic_preprocess(img, image_size=input_size, use_thumbnail=True, max_num=max_num)
        pixel_values = [transform(tile) for tile in img]
        pixel_values = torch.stack(pixel_values)
        num_patches_list.append(pixel_values.shape[0])
        pixel_values_list.append(pixel_values)
    pixel_values = torch.cat(pixel_values_list)
    return pixel_values, num_patches_list

video_path = './examples/red-panda.mp4'
pixel_values, num_patches_list = load_video(video_path, num_segments=8, max_num=1)
pixel_values = pixel_values.to(torch.bfloat16).cuda()
video_prefix = ''.join([f'Frame{i+1}: <image>\n' for i in range(len(num_patches_list))])
question = video_prefix + 'What is the red panda doing?'
# Frame1: <image>\nFrame2: <image>\n...\nFrame8: <image>\n{question}
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list, history=None, return_history=True)
print(f'User: {question}\nAssistant: {response}')

question = 'Describe this video in detail. Don\'t repeat.'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list, history=history, return_history=True)
print(f'User: {question}\nAssistant: {response}')

Streaming output

Besides this method, you can also use the following code to get streamed output.

from transformers import TextIteratorStreamer
from threading import Thread

# Initialize the streamer
streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True, timeout=10)
# Define the generation configuration
generation_config = dict(max_new_tokens=1024, do_sample=False, streamer=streamer)
# Start the model chat in a separate thread
thread = Thread(target=model.chat, kwargs=dict(
    tokenizer=tokenizer, pixel_values=pixel_values, question=question,
    history=None, return_history=False, generation_config=generation_config,
))
thread.start()

# Initialize an empty string to store the generated text
generated_text = ''
# Loop through the streamer to get the new text as it is generated
for new_text in streamer:
    if new_text == model.conv_template.sep:
        break
    generated_text += new_text
    print(new_text, end='', flush=True)  # Print each new chunk of generated text on the same line

Finetune

Many repositories now support fine-tuning of the InternVL series models, including InternVL, SWIFT, XTurner, and others. Please refer to their documentation for more details on fine-tuning.

Deployment

LMDeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by the MMRazor and MMDeploy teams.

pip install lmdeploy==0.5.3

LMDeploy abstracts the complex inference process of multi-modal Vision-Language Models (VLM) into an easy-to-use pipeline, similar to the Large Language Model (LLM) inference pipeline.

A 'Hello, world' example 

from lmdeploy import pipeline, TurbomindEngineConfig
from lmdeploy.vl import load_image

model = 'OpenGVLab/Mono-InternVL-2B'
image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
response = pipe(('describe this image', image))
print(response.text)

If ImportError occurs while executing this case, please install the required dependency packages as prompted.

Multi-images inference

When dealing with multiple images, you can put them all in one list. Keep in mind that multiple images will lead to a higher number of input tokens, and as a result, the size of the context window typically needs to be increased.

Warning: Due to the scarcity of multi-image conversation data, the performance on multi-image tasks may be unstable, and it may require multiple attempts to achieve satisfactory results.

from lmdeploy import pipeline, TurbomindEngineConfig
from lmdeploy.vl import load_image
from lmdeploy.vl.constants import IMAGE_TOKEN

model = 'OpenGVLab/Mono-InternVL-2B'
pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))

image_urls=[
    'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg',
    'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg'
]

images = [load_image(img_url) for img_url in image_urls]
# Numbering images improves multi-image conversations
response = pipe((f'Image-1: {IMAGE_TOKEN}\nImage-2: {IMAGE_TOKEN}\ndescribe these two images', images))
print(response.text)

Batch prompts inference

Conducting inference with batch prompts is quite straightforward; just place them within a list structure:

from lmdeploy import pipeline, TurbomindEngineConfig
from lmdeploy.vl import load_image

model = 'OpenGVLab/Mono-InternVL-2B'
pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))

image_urls=[
    "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg",
    "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg"
]
prompts = [('describe this image', load_image(img_url)) for img_url in image_urls]
response = pipe(prompts)
print(response)

Multi-turn conversation

There are two ways to do the multi-turn conversations with the pipeline. One is to construct messages according to the format of OpenAI and use above introduced method, the other is to use the pipeline.chat interface.

from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig
from lmdeploy.vl import load_image

model = 'OpenGVLab/Mono-InternVL-2B'
pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))

image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg')
gen_config = GenerationConfig(top_k=40, top_p=0.8, temperature=0.8)
sess = pipe.chat(('describe this image', image), gen_config=gen_config)
print(sess.response.text)
sess = pipe.chat('What is the woman doing?', session=sess, gen_config=gen_config)
print(sess.response.text)

Service

LMDeploy's api_server enables models to be easily packed into services with a single command. The provided RESTful APIs are compatible with OpenAI's interfaces. Below are an example of service startup:

lmdeploy serve api_server OpenGVLab/Mono-InternVL-2B --backend turbomind --server-port 23333

To use the OpenAI-style interface, you need to install OpenAI:

pip install openai

Then, use the code below to make the API call:

from openai import OpenAI

client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1')
model_name = client.models.list().data[0].id
response = client.chat.completions.create(
    model=model_name,
    messages=[{
        'role':
        'user',
        'content': [{
            'type': 'text',
            'text': 'describe this image',
        }, {
            'type': 'image_url',
            'image_url': {
                'url':
                'https://modelscope.oss-cn-beijing.aliyuncs.com/resource/tiger.jpeg',
            },
        }],
    }],
    temperature=0.8,
    top_p=0.8)
print(response)

License

This project is released under the MIT license, while InternLM2 is licensed under the Apache-2.0 license.

Citation

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

@article{luo2024mono,
  title={Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training},
  author={Luo, Gen and Yang, Xue and Dou, Wenhan and Wang, Zhaokai and Dai, Jifeng and Qiao, Yu and Zhu, Xizhou},
  journal={arXiv preprint arXiv:2410.TODO},
  year={2024}
}

简介

我们发布了Mono-InternVL，这是一种单体化的多模态大语言模型（MLLM），将视觉编码和文本解码集成到一个单一的大语言模型中。在Mono-InternVL中，一组视觉专家通过专家混合机制嵌入到预训练的LLM中。通过冻结LLM的语言部分参数，Mono-InternVL确保了视觉能力的优化，同时不会影响预训练的语言知识。基于这一结构，我们引入了内源视觉预训练（Endogenous Visual Pretraining, EViP），实现了由粗粒度到精粒度的视觉学习。

Mono-InternVL在性能上优于当前最先进的MLLM Mini-InternVL-2B-1.5，并且显著超越了其他单体化MLLMs，如上方的雷达图所示。同时，它的部署效率也得到了提升，首个token的延迟降低了最多达67%。

本仓库包含了经过指令微调的Mono-InternVL-2B模型，它是基于internlm2-chat-1_8b搭建的。更多详细信息，请参阅我们的论文。

性能测试

评测数据集 Chameleon-7B EVE-7B (HD) Emu3 Mini-InternVL-2B-1-5 Mono-InternVL-2B
模型种类 单体化 单体化 单体化 模块化 单体化
激活参数 7B 7B 8B 2.2B 1.8B
MMVet 8.3 25.7 37.2 39.3 40.1
MMMUval 25.4 32.6 31.6 34.6 33.7
MMEsum 170 1628 — 1902 1875
MMBench-ENtest 31.1 52.3 58.5 70.9 65.5
MathVistatestmini 22.3 34.2 — 41.1 45.7
SEED-Image 30.6 64.6 68.2 69.8 67.4
OCRBench 7 398 687 654 767
Hallusion-Bench 17.1 26.4 — 37.5 34.8
CCBenchdev 3.5 16.3 — 63.5 66.3
Avgmultimodal 16.1 38.9 — 54.4 55.2
TextVQAval 4.8 56.8 64.7 70.5 72.6
SQA-Itest 47.2 64.9 89.2 84.9 93.6
GQAtest — 62.6 60.3 61.6 59.5
DocVQAtest 1.5 53.0 76.3 85.0 80.0
AI2Dtest 46.0 61.0 70.0 69.8 68.6
ChartQAtest 2.9 59.1 68.6 74.8 73.7
InfoVQAtest 5.0 25.0 43.8 55.4 43.0
AvgVQA 17.9 54.6 67.6 71.7 70.1
  • 以上结果的来源包括相应的原始论文、我们基于VLMEvalKit的评测，以及OpenCompass。
  • 平均分数Avg通过将每个指标归一化到0至100之间来计算。
  • 请注意，使用不同的测试工具包评估同一模型可能会导致细微差异，这是正常的。代码版本的更新、环境和硬件的变化也可能导致结果的微小差异。

快速启动

我们提供了一个示例代码，用于使用 transformers 运行 Mono-InternVL-2B。

请使用 transformers==4.37.2 以确保模型正常运行。

示例代码请点击这里。

微调

许多仓库现在都支持 InternVL 系列模型的微调，包括 InternVL、SWIFT、XTurner 等。请参阅它们的文档以获取更多微调细节。

部署

LMDeploy

LMDeploy 是由 MMRazor 和 MMDeploy 团队开发的用于压缩、部署和服务大语言模型（LLM）的工具包。

pip install lmdeploy==0.5.3

LMDeploy 将多模态视觉-语言模型（VLM）的复杂推理过程抽象为一个易于使用的管道，类似于大语言模型（LLM）的推理管道。

一个“你好，世界”示例 

from lmdeploy import pipeline, TurbomindEngineConfig
from lmdeploy.vl import load_image

model = 'OpenGVLab/Mono-InternVL-2B'
image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
response = pipe(('describe this image', image))
print(response.text)

如果在执行此示例时出现 ImportError，请按照提示安装所需的依赖包。

多图像推理

在处理多张图像时，可以将它们全部放入一个列表中。请注意，多张图像会导致输入 token 数量增加，因此通常需要增加上下文窗口的大小。

from lmdeploy import pipeline, TurbomindEngineConfig
from lmdeploy.vl import load_image
from lmdeploy.vl.constants import IMAGE_TOKEN

model = 'OpenGVLab/Mono-InternVL-2B'
pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))

image_urls=[
    'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg',
    'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg'
]

images = [load_image(img_url) for img_url in image_urls]
# Numbering images improves multi-image conversations
response = pipe((f'Image-1: {IMAGE_TOKEN}\nImage-2: {IMAGE_TOKEN}\ndescribe these two images', images))
print(response.text)

批量Prompt推理

使用批量Prompt进行推理非常简单；只需将它们放在一个列表结构中：

from lmdeploy import pipeline, TurbomindEngineConfig
from lmdeploy.vl import load_image

model = 'OpenGVLab/Mono-InternVL-2B'
pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))

image_urls=[
    "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg",
    "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/det.jpg"
]
prompts = [('describe this image', load_image(img_url)) for img_url in image_urls]
response = pipe(prompts)
print(response)

多轮对话

使用管道进行多轮对话有两种方法。一种是根据 OpenAI 的格式构建消息并使用上述方法，另一种是使用 pipeline.chat 接口。

from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig
from lmdeploy.vl import load_image

model = 'OpenGVLab/Mono-InternVL-2B'
pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))

image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg')
gen_config = GenerationConfig(top_k=40, top_p=0.8, temperature=0.8)
sess = pipe.chat(('describe this image', image), gen_config=gen_config)
print(sess.response.text)
sess = pipe.chat('What is the woman doing?', session=sess, gen_config=gen_config)
print(sess.response.text)

API部署

LMDeploy 的 api_server 使模型能够通过一个命令轻松打包成服务。提供的 RESTful API 与 OpenAI 的接口兼容。以下是服务启动的示例：

lmdeploy serve api_server OpenGVLab/Mono-InternVL-2B --backend turbomind --server-port 23333

为了使用OpenAI风格的API接口，您需要安装OpenAI:

pip install openai

然后，使用下面的代码进行API调用:

from openai import OpenAI

client = OpenAI(api_key='YOUR_API_KEY', base_url='http://0.0.0.0:23333/v1')
model_name = client.models.list().data[0].id
response = client.chat.completions.create(
    model=model_name,
    messages=[{
        'role':
        'user',
        'content': [{
            'type': 'text',
            'text': 'describe this image',
        }, {
            'type': 'image_url',
            'image_url': {
                'url':
                'https://modelscope.oss-cn-beijing.aliyuncs.com/resource/tiger.jpeg',
            },
        }],
    }],
    temperature=0.8,
    top_p=0.8)
print(response)

开源许可证

该项目采用 MIT 许可证发布，而 InternLM2 则采用 Apache-2.0 许可证。

引用

如果您发现此项目对您的研究有用，可以考虑引用我们的论文：

@article{luo2024mono,
  title={Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training},
  author={Luo, Gen and Yang, Xue and Dou, Wenhan and Wang, Zhaokai and Dai, Jifeng and Qiao, Yu and Zhu, Xizhou},
  journal={arXiv preprint arXiv:2410.TODO},
  year={2024}
}