license: mit library_name: transformers pipeline_tag: image-text-to-text

mmMamba-linear 模型卡片

简介

我们提出了mmMamba，这是首个通过中等学术计算资源实现二次到线性蒸馏的纯解码器多模态状态空间模型。与现有基于线性复杂度编码器的多模态大语言模型（MLLMs）不同，mmMamba无需依赖独立的视觉编码器和性能欠佳的基于RNN的预训练LLMs。通过我们的种子策略和三阶段渐进式蒸馏方案，mmMamba有效迁移了二次复杂度纯解码器预训练MLLMs的知识，同时保留了多模态能力。此外，mmMamba引入了灵活的混合架构，策略性地结合Transformer和Mamba层，实现了计算效率与模型性能的可定制权衡。

基于纯Mamba-2架构的mmMamba-linear蒸馏自纯解码器模型HoVLE-2.6B，其性能可媲美现有线性和二次复杂度视觉语言模型（VLMs），包括参数规模两倍于它的EVE-7B等模型。混合变体mmMamba-hybrid则进一步提升了所有基准测试的表现，接近教师模型HoVLE的能力。在103K tokens的长上下文场景中，mmMamba-linear相比HoVLE实现了20.6倍加速和75.8%的GPU内存节省，而mmMamba-hybrid则实现了13.5倍加速和60.2%的内存节省。

mmMamba的种子策略和三阶段蒸馏流程

论文: https://hf.co/papers/2502.13145

代码: https://github.com/hustvl/mmMamba

mmMamba推理快速入门指南

我们提供使用Transformers库运行mmMamba推理的示例代码。

模型推理主要依赖

以下是模型推理所需的主要依赖项：

• torch==2.1.0
• torchvision==0.16.0
• torchaudio==2.1.0
• transformers==4.37.2
• peft==0.10.0
• triton==3.2.0
• mamba_ssm
• causal_conv1d
• flash_attn （请根据您的环境选择下载对应的.whl文件）
• peft
• omegaconf
• rich
• accelerate
• sentencepiece
• decord
• seaborn

使用Transformers进行推理

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

    # 计算现有图像的宽高比
    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])

    # 找到最接近目标宽高比的比例
    target_aspect_ratio = find_closest_aspect_ratio(
        aspect_ratio, target_ratios, orig_width, orig_height, image_size)

    # 计算目标宽度和高度
    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]

    # 调整图像大小
    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
        )
        # 分割图像
        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


path = 'hustvl/mmMamba-linear'
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=False,
    trust_remote_code=True).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)

# 在`max_num`中设置最大分块数
pixel_values = load_image('/path/to/image', max_num=12).to(torch.bfloat16).cuda()
generation_config = dict(max_new_tokens=1024, do_sample=True)

# 纯文本对话
question = '你好，你是谁？'
response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
print(f'用户: {question}\n助手: {response}')


# 单图像单轮对话
question = '<image>\n请简要描述这张图片。'
response = model.chat(tokenizer, pixel_values, question, generation_config)
print(f'用户: {question}\n助手: {response}')