魔搭ModelScope社区 2024年12月09日
魔搭社区每周速递（12.01-12.07）
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

魔搭ModelScope社区近期更新了1338个模型,包括HunyuanVideo、InternVL2.5系列等,新增82个数据集,如OpenO1-SFT、LLaVA-CoT-o1-Instruct等,以及26个创新应用,如OminiControl、Hallo等.此外,社区还发布了8篇技术文章,内容涵盖NexaAI、魔搭AIGC12月赛题、免费模型推理API、2024“AI+硬件创新大赛”获奖名单、腾讯开源混元视频生成模型、金融行业大模型挑战赛、智源研究院中文高质量数据集CCI3.0-HQ技术报告以及用OpenVINO™部署GLM-Edge全家桶.

🎞️HunyuanVideo是腾讯开源的一个具有超过130亿参数的先进开源视频生成模型，它通过集成数据管理、图像-视频联合训练和高效基础设施的综合框架，以及有效的模型架构和数据集扩展策略，实现了高视觉质量、运动多样性、文本-视频对齐和生成稳定性。

🖼️InternVL 2.5是上海人工智能实验室开源的一个先进的多模态大型语言模型（MLLM）系列，基于InternVL 2.0的核心模型架构，在训练、测试策略以及数据质量方面作显著增强，通过对包括多学科推理、文档理解、多图像/视频理解、现实世界理解、多模态幻觉检测、视觉锚定、多语言能力和纯语言处理等广泛基准的深入评估，是第一个在MMMU基准上超过70%的开源MLLM。

💻社区发布了8篇技术文章，内容涵盖了NexaAI、魔搭AIGC12月赛题、免费模型推理API、2024“AI+硬件创新大赛”获奖名单、腾讯开源混元视频生成模型、金融行业大模型挑战赛、智源研究院中文高质量数据集CCI3.0-HQ技术报告以及用OpenVINO™部署GLM-Edge全家桶。

👨‍💻魔搭ModelScope社区近期更新了1338个模型，新增82个数据集以及26个创新应用，为开发者提供了丰富的资源和工具。

🏆2024“AI+硬件创新大赛”获奖名单出炉，浙大、上交与复旦联队等夺冠，展示了高校在AI领域的创新实力。

2024-12-08 22:34 浙江

1338模型、82数据集、26创新应用、8篇文章

?魔搭ModelScope本期社区进展：

?1338个模型：HunyuanVideo、InternVL2.5系列、TeleChat2系列、AWPortraitCN、fish-speech-1.5、Mistral-Nemo-Instruct-2407-FP等；

?82个数据集：OpenO1-SFT、LLaVA-CoT-o1-Instruct、LLaVA-CoT-100k等；

?26个创新应用：OminiControl、Hallo、HunyuanVideo等；

? 8篇内容：


01


精选模型


HunyuanVideo

HunyuanVideo是腾讯开源的一个具有超过130亿参数的先进开源视频生成模型，它通过集成数据管理、图像-视频联合训练和高效基础设施的综合框架，以及有效的模型架构和数据集扩展策略，实现了高视觉质量、运动多样性、文本-视频对齐和生成稳定性。


模型链接：

https://modelscope.cn/models/AI-ModelScope/HunyuanVideo


代码示例：

详见 腾讯开源混元视频生成模型，这效果！太稳了吧！


InternVL2.5系列

InternVL 2.5是上海人工智能实验室开源的一个先进的多模态大型语言模型（MLLM）系列，基于InternVL 2.0的核心模型架构，在训练、测试策略以及数据质量方面作显著增强，通过对包括多学科推理、文档理解、多图像/视频理解、现实世界理解、多模态幻觉检测、视觉锚定、多语言能力和纯语言处理等广泛基准的深入评估，是第一个在MMMU基准上超过70%的开源MLLM。


模型链接：

https://www.modelscope.cn/models/OpenGVLab/InternVL2_5-1B/summary


https://www.modelscope.cn/models/OpenGVLab/InternVL2_5-2B


https://www.modelscope.cn/models/OpenGVLab/InternVL2_5-4B


https://www.modelscope.cn/models/OpenGVLab/InternVL2_5-8B


https://www.modelscope.cn/models/OpenGVLab/InternVL2_5-26B


https://www.modelscope.cn/models/OpenGVLab/InternVL2_5-38B


https://www.modelscope.cn/models/OpenGVLab/InternVL2_5-78B


代码示例：

transformers推理代码（以InternVL2_5-4B推理为例）：

import numpy as npimport torchimport torchvision.transforms as Tfrom decord import VideoReader, cpufrom PIL import Imagefrom torchvision.transforms.functional import InterpolationModefrom modelscope 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/InternVL2_5-4B'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('./awesome.png', 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('./awesome.png', max_num=12).to(torch.bfloat16).cuda()pixel_values2 = load_image('./noword.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('./awesome.png', max_num=12).to(torch.bfloat16).cuda()pixel_values2 = load_image('./noword.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('./awesome.png', max_num=12).to(torch.bfloat16).cuda()pixel_values2 = load_image('./noword.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 = './showcase.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}')


 TeleChat2

星辰语义大模型TeleChat2是由中国电信人工智能研究院研发训练的大语言模型。


TeleChat2系列模型包括TeleChat2-3B、TeleChat2-7B、TeleChat2-35B和TeleChat2-115B，具备显著的工具调用功能和优化的Function Call表现，相较同尺寸模型在多个榜单中表现优异。


该系列在训练数据和方法方面进行了全面改进，通用问答及逻辑推理等能力较前代提升超过29%。所有模型均在国产算力和深度学习框架上训练，保障了自主可控性。通过优化MP、PP、SP实现和长文训练技术，提升了模型性能和训练速度。

模型链接：

https://modelscope.cn/models/TeleAI/TeleChat2-3B


https://modelscope.cn/models/TeleAI/TeleChat2-7B


https://modelscope.cn/models/TeleAI/TeleChat2-35B-Nov


https://modelscope.cn/models/TeleAI/TeleChat2-115B


代码示例：

当前模型推理兼容了单卡和多卡推理，以及针对长文推理做了部分优化工作，模型推理方法示范：

import osimport torchfrom modelscope import AutoModelForCausalLM, AutoTokenizer, GenerationConfigtokenizer = AutoTokenizer.from_pretrained('TeleAI/TeleChat2-3B', trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained('TeleAI/TeleChat2-3B', trust_remote_code=True, device_map="auto",                                                  torch_dtype=torch.float16)prompt = "生抽与老抽的区别？"messages = [{"role": "user", "content": prompt}]text = tokenizer.apply_chat_template(messages,  tokenize=False,       add_generation_prompt=True)model_inputs = tokenizer([text], return_tensors="pt").to(model.device)generated_ids = model.generate(    **model_inputs,    max_new_tokens=512)generated_ids = [    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)]



AWPortraitCN

AWPortraitCN 是基于FLUX.1-dev开发。它在训练时使用了更符合中国人外貌和审美特征的图像。它包含了多种类型的肖像，如室内和室外肖像、时尚和影棚照片。它具有很强的泛化能力。与原始版本相比，AWPortraitCN在皮肤质感上更加细腻真实。为了追求更真实的原始图像效果，它可以与AWPortraitSR工作流程一起使用。


模型链接：

https://modelscope.cn/models/LiblibAI/AWPortraitCN


效果展示：



02


数据集推荐



DAVIS-Edit

数据集专为通过SFT微调语言模型以激活思维链而设计，目的是提升模型在复杂推理任务上生成连贯、逻辑性强的推理序列的能力。


数据集链接：

https://modelscope.cn/datasets/AI-ModelScope/OpenO1-SFT


LLaVA-CoT-o1-Instruct

LLaVA-CoT-o1-Instruct是用于支持和提升语言模型在复杂任务中的逻辑推理和连贯性表现。


数据集链接：

https://modelscope.cn/datasets/AI-ModelScope/LLaVA-CoT-o1-Instruct


LLaVA-CoT-100k

LLaVA-CoT-100k是一个专注于复杂推理任务的数据集，包含100,000个样本。这个数据集被设计用来训练和测试语言模型，以提高它们在逻辑推理和问题解决方面的能力。


数据集链接：

https://modelscope.cn/datasets/AI-ModelScope/LLaVA-CoT-100k


03


精选应用



OminiControl

是一款内容生成工具，支持上传一张有主体的图片+一段文本关键词进行合成。具有广泛的应用前景。


体验直达：

https://modelscope.cn/studios/AI-ModelScope/OminiControl



Hallo

TTS x Hallo Talking Portrait Generator是一个集成多个开源项目的演示工具，允许用户生成会说话的肖像视频，但视频长度限制为4秒音频以内。


体验直达：

https://modelscope.cn/studios/AI-ModelScope/Hallo



HunyuanVideo

HunyuanVideo是一个创新的视频生成工具，它通过引入Transformer架构和Full Attention机制，实现了图像和视频的统一生成。该工具采用“Dual-stream to Single-stream”混合模型设计，首先独立处理视频和文本token，确保每个模态都能学习到适合自己的调制机制，然后在Single-stream阶段将视频和文本token融合，实现多模态信息的有效整合，捕捉视觉和语义信息之间的复杂交互，从而显著提升模型的整体性能。


体验直达：

https://modelscope.cn/studios/chuanSir/HunyuanVideo


04


社区精选文章




?点击关注ModelScope公众号获取

更多技术信息~






跳转微信打开

Fish AI Reader

Fish AI Reader

AI辅助创作，多种专业模板，深度分析，高质量内容生成。从观点提取到深度思考，FishAI为您提供全方位的创作支持。新版本引入自定义参数，让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅，AI 时代的下一个智能信息助手，助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

魔搭ModelScope 人工智能 开源模型 视频生成 多模态
相关文章
人工智能正在摧毁互联网内容生态系统
阿里云：通义千问API日调用量破亿 企业用户破9万
【iThome 2024 CIO大調查系列1】AI、資安和永續變革三箭齊發
鈺登跨入AI，推出搭配英特爾四代Xeon SP與Gaudi2的伺服器
蘋果發表M4晶片，更新iPad產品線
Red Hat推出AI平臺，內建IBM開源Granite模型
【iThome 2024 CIO大調查系列 1｜IT投資趨勢】IT投資布局更多角化，雲端比重明顯增加