Internvl3 8B AWQ

🚀 InternVL3-8B

InternVL3-8B 是先进的多模态大语言模型（MLLM）系列，相比前代模型，在多模态感知、推理等能力上有显著提升，还拓展了工具使用、GUI 代理、工业图像分析、3D 视觉感知等多模态能力。

📂 GitHub 📜 InternVL 1.0 📜 InternVL 1.5 📜 InternVL 2.5 📜 InternVL2.5-MPO 📜 InternVL3

🆕 Blog 🗨️ Chat Demo 🤗 HF Demo 🚀 Quick Start 📖 Documents

🚀 快速开始

我们提供了使用 transformers 运行 InternVL3-8B 的示例代码。

请使用 transformers>=4.37.2 以确保模型正常工作。

模型加载

16 位（bf16 / fp16）

import torch
from transformers import AutoTokenizer, AutoModel
path = "OpenGVLab/InternVL3-8B"
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 位量化

import torch
from transformers import AutoTokenizer, AutoModel
path = "OpenGVLab/InternVL3-8B"
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()

多 GPU 情况

为避免多 GPU 推理时因张量不在同一设备而出现错误，我们确保大语言模型（LLM）的第一层和最后一层在同一设备上。

import math
import torch
from transformers import AutoTokenizer, AutoModel

def split_model(model_name):
    device_map = {}
    world_size = torch.cuda.device_count()
    config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
    num_layers = config.llm_config.num_hidden_layers
    # 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.model.rotary_emb'] = 0
    device_map['language_model.lm_head'] = 0
    device_map[f'language_model.model.layers.{num_layers - 1}'] = 0

    return device_map

path = "OpenGVLab/InternVL3-8B"
device_map = split_model('InternVL3-8B')
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()

使用 Transformers 进行推理

import math
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

def split_model(model_name):
    device_map = {}
    world_size = torch.cuda.device_count()
    config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
    num_layers = config.llm_config.num_hidden_layers
    # 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.model.rotary_emb'] = 0
    device_map['language_model.lm_head'] = 0
    device_map[f'language_model.model.layers.{num_layers - 1}'] = 0

    return device_map

# If you set `load_in_8bit=True`, you will need two 80GB GPUs.
# If you set `load_in_8bit=False`, you will need at least three 80GB GPUs.
path = 'OpenGVLab/InternVL3-8B'
device_map = split_model('InternVL3-8B')
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    load_in_8bit=False,
    low_cpu_mem_usage=True,
    use_flash_attn=True,
    trust_remote_code=True,
    device_map=device_map).eval()
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.'
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}')

流式输出

除上述方法外，你还可以使用以下代码实现流式输出。

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

✨ 主要特性

• 先进的多模态能力：相比 InternVL 2.5，InternVL3 展现出更卓越的多模态感知和推理能力，还将多模态能力拓展到工具使用、GUI 代理、工业图像分析、3D 视觉感知等领域。
• 统一的预训练方法：提出原生多模态预训练方法，将语言和视觉学习整合到一个预训练阶段，提升模型处理视觉 - 语言任务的能力。
• 灵活的位置编码：集成可变视觉位置编码（V2PE），使模型在长上下文理解方面表现更优。
• 高效的训练策略：采用混合偏好优化（MPO）和测试时缩放等策略，提高模型的推理性能。

📦 安装指南

LMDeploy

LMDeploy 是用于压缩、部署和服务大语言模型（LLM）和视觉语言模型（VLM）的工具包。

# 如果 lmdeploy<0.7.3，需要显式设置 chat_template_config=ChatTemplateConfig(model_name='internvl2_5')
pip install lmdeploy>=0.7.3

💻 使用示例

基础用法

# 纯文本对话示例
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}')

高级用法

# 多图多轮对话示例
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}')

📚 详细文档

模型架构

InternVL3 沿用了 InternVL 2.5 及其前代模型（InternVL 1.5 和 2.0）的“ViT - MLP - LLM”范式。在新版本中，我们使用随机初始化的 MLP 投影器，将新的增量预训练的 InternViT 与各种预训练的大语言模型（如 InternLM 3 和 Qwen 2.5）集成。

与之前版本一样，我们应用了像素重排操作，将视觉标记数量减少到原来的四分之一。此外，我们采用了与 InternVL 1.5 类似的动态分辨率策略，将图像分割成 448×448 像素的图块。从 InternVL 2.0 开始，关键的区别在于我们还引入了对多图像和视频数据的支持。

值得注意的是，在 InternVL3 中，我们集成了 可变视觉位置编码（V2PE），它为视觉标记使用更小、更灵活的位置增量。得益于 V2PE，InternVL3 与其前代模型相比，展现出更好的长上下文理解能力。

训练策略

原生多模态预训练

我们提出了 原生多模态预训练 方法，将语言和视觉学习整合到一个预训练阶段。与先训练纯语言模型，然后使其适应处理其他模态的标准范式不同，我们的方法将多模态数据（如图像 - 文本、视频 - 文本或图像 - 文本交错序列）与大规模文本语料库交织在一起。这种统一的训练方案使模型能够同时学习语言和多模态表示，最终提高其处理视觉 - 语言任务的能力，而无需单独的对齐或桥接模块。更多细节请参考 我们的论文。

监督微调

在这个阶段，InternVL2.5 中提出的随机 JPEG 压缩、平方损失重新加权和多模态数据打包技术也应用于 InternVL3 系列。与 InternVL2.5 相比，InternVL3 监督微调阶段的主要进步在于使用了更高质量和更多样化的训练数据。具体来说，我们进一步扩展了工具使用、3D 场景理解、GUI 操作、长上下文任务、视频理解、科学图表、创意写作和多模态推理的训练样本。

混合偏好优化

在预训练和监督微调期间，模型根据之前的真实标记来预测下一个标记。然而，在推理期间，模型根据自己的先前输出预测每个标记。真实标记和模型预测标记之间的这种差异引入了分布偏移，这可能会损害模型的思维链（CoT）推理能力。为缓解这个问题，我们采用了 MPO，它引入了来自正样本和负样本的额外监督，以使模型响应分布与真实分布对齐，从而提高推理性能。具体来说，MPO 的训练目标是偏好损失 \(\mathcal{L}{\text{p}}\)、质量损失 \(\mathcal{L}{\text{q}}\) 和生成损失 \(\mathcal{L}_{\text{g}}\) 的组合，可以表述如下：

$$ \mathcal{L}=w_{p}\cdot\mathcal{L}{\text{p}} + w{q}\cdot\mathcal{L}{\text{q}} + w{g}\cdot\mathcal{L}_{\text{g}}, $$

其中 \(w_{*}\) 表示每个损失组件的权重。有关 MPO 的更多细节，请参考 我们的论文。

测试时缩放

测试时缩放已被证明是增强大语言模型和多模态大语言模型推理能力的有效方法。在这项工作中，我们使用 Best - of - N 评估策略，并使用 VisualPRM - 8B 作为评判模型，为推理和数学评估选择最佳响应。

多模态能力评估

多模态推理和数学

OCR、图表和文档理解

多图像和现实世界理解

综合多模态和幻觉评估

视觉定位

多模态多语言理解

视频理解

GUI 定位

空间推理

语言能力评估

我们将 InternVL3 与 Qwen2.5 聊天模型进行了比较，Qwen2.5 的对应预训练基础模型被用作 InternVL3 语言组件的初始化。得益于原生多模态预训练，InternVL3 系列在整体文本性能上甚至优于 Qwen2.5 系列。请注意，Qwen2.5 系列的评估分数可能与官方报告的不同，因为我们在所有数据集上采用了表中提供的提示版本进行 OpenCompass 评估。

消融研究

原生多模态预训练

我们在 InternVL2 - 8B 模型上进行了实验，同时保持其架构、初始化参数和训练数据完全不变。传统上，InternVL2 - 8B 采用的训练流程是先进行 MLP 预热阶段以进行特征对齐，然后进行指令调优阶段。在我们的实验中，我们用原生多模态预训练过程取代了传统的 MLP 预热阶段。这种修改隔离了原生多模态预训练对模型整体多模态能力的贡献。

下图中的评估结果表明，采用原生多模态预训练的模型在大多数基准测试中的表现与经过完整多阶段训练的 InternVL2 - 8B 基线相当。此外，当在更高质量的数据上进行指令调优后，该模型在评估的多模态任务中表现出进一步的性能提升。这些发现强调了原生多模态预训练在赋予多模态大语言模型强大多模态能力方面的效率。

混合偏好优化

如下表所示，与未使用 MPO 进行微调的模型相比，使用 MPO 进行微调的模型在七个多模态推理基准测试中表现出更优的推理性能。具体来说，InternVL3 - 78B 和 InternVL3 - 38B 分别比其对应模型高出 4.1 和 4.5 分。值得注意的是，MPO 使用的训练数据是监督微调使用数据的子集，这表明性能提升主要源于训练算法而非训练数据。

可变视觉位置编码

如下表所示，引入 V2PE 导致大多数评估指标的性能显著提升。此外，我们通过改变位置增量 \( \delta \) 进行的消融研究表明，即使对于主要涉及传统上下文的任务，相对较小的 \( \delta \) 值也能实现最佳性能。这些发现为未来改进多模态大语言模型中视觉标记的位置编码策略提供了重要见解。

🔧 技术细节

模型家族

模型名称	视觉部分	语言部分	HF 链接
InternVL3 - 1B	InternViT - 300M - 448px - V2_5	Qwen2.5 - 0.5B	🤗 link
InternVL3 - 2B	InternViT - 300M - 448px - V2_5	Qwen2.5 - 1.5B	🤗 link
InternVL3 - 8B	InternViT - 300M - 448px - V2_5	Qwen2.5 - 7B	🤗 link
InternVL3 - 9B	InternViT - 300M - 448px - V2_5	internlm3 - 8b - instruct	🤗 link
InternVL3 - 14B	InternViT - 300M - 448px - V2_5	Qwen2.5 - 14B	🤗 link
InternVL3 - 38B	InternViT - 6B - 448px - V2_5	Qwen2.5 - 32B	🤗 link
InternVL3 - 78B	InternViT - 6B - 448px - V2_5	Qwen2.5 - 72B	🤗 link

📄 许可证

本项目遵循 MIT 许可证发布。本项目使用预训练的 Qwen2.5 作为组件，Qwen2.5 遵循 Qwen 许可证。

引用

如果您在研究中发现本项目有用，请考虑引用以下文献：

@article{chen2024expanding,
  title={Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling},
  author={Chen, Zhe and Wang, Weiyun and Cao, Yue and Liu, Yangzhou and Gao, Zhangwei and Cui, Erfei and Zhu, Jinguo and Ye, Shenglong and Tian, Hao and Liu, Zhaoyang and others},
  journal={arXiv preprint arXiv:2412.05271},
  year={2024}
}
@article{wang2024mpo,
  title={Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization},
  author={Wang, Weiyun and Chen, Zhe and Wang, Wenhai and Cao, Yue and Liu, Yangzhou and Gao, Zhangwei and Zhu, Jinguo and Zhu, Xizhou and Lu, Lewei and Qiao, Yu and Dai, Jifeng},
  journal={arXiv preprint arXiv:2411.10442},
  year={2024}
}
@article{chen2024far,
  title={How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites},
  author={Chen, Zhe and Wang, Weiyun and Tian, Hao and Ye, Shenglong and Gao, Zhangwei and Cui, Erfei and Tong, Wenwen and Hu, Kongzhi and Luo, Jiapeng and Ma, Zheng and others},
  journal={arXiv preprint arXiv:2404.16821},
  year={2024}
}
@inproceedings{chen2024internvl,
  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 others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={24185--24198},
  year={2024}
}