Initial commit

Dockerfile

+FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.3.0-py3.10-dtk24.04.3-ubuntu20.04
\ No newline at end of file

README.md

+# InterVL2.5
+## 论文
+
+[Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://arxiv.org/abs/2412.05271)
+
+
+## 模型结构
+InternVL 2.5保留了与InternVL 1.5[35]相同的模型架构，并且
+InternVL 2.0，即广泛使用的“ViT-MLP-LLM”范式，结合了预先训练的InternViT-300M
+或通过MLP投影仪具有各种尺寸的LLM[19，229]的InternViT-6B。与之前的版本一致，
+我们应用像素反洗牌操作来减少每个448 × 448图像块产生的1024个视觉令牌
+到256个代币。此外，与InternVL 1.5相比，InternVL 2.0和2.5引入了额外的数据类型，
+将多图像和视频数据与现有的单图像和纯文本数据合并。
+
+
+
+<div align=center>
+    <img src="./Pic/arch.png"/>
+</div>
+
+## 算法原理
+
+InternVL 2.5训练过程分为三个阶段——阶段1（MLP预热）可选阶段1.5（ViT增量学习）和阶段2（全模型指令调优）。多阶段设计逐步增强视觉-语言对齐，稳定培训，并为与更大的LLM集成准备模块。(b)逐步扩大战略。在早期阶段用较小的LLM训练的ViT模块可以很容易地与较大的LLM集成，以可承受的资源开销实现可扩展的模型对齐。
+
+<div align=center>
+    <img src="./Pic/theory.png"/>
+</div>
+
+## 环境配置
+### Docker（方法一）
+推荐使用docker方式运行， 此处提供[光源](https://www.sourcefind.cn/#/service-details)拉取docker镜像的地址与使用步骤
+```
+docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.3.0-py3.10-dtk24.04.3-ubuntu20.04
+docker run -it --shm-size=1024G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name internvl  <your IMAGE ID> bash # <your IMAGE ID>为以上拉取的docker的镜像ID替换
+
+git clone http://developer.sourcefind.cn/codes/modelzoo/internvl2.5_pytorch.git
+
+cd /path/your_code_data/
+
+pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+```
+Tips:以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应。
+### Dockerfile（方法二）
+此处提供dockerfile的使用方法
+```
+docker build -t internvl:latest .
+docker run --shm-size 500g --network=host --name=internvl --privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v 项目地址(绝对路径):/home/ -v /opt/hyhal:/opt/hyhal:ro -it <your IMAGE ID> bash
+
+
+git clone http://developer.sourcefind.cn/codes/modelzoo/internvl2.5_pytorch.git
+
+cd /path/your_code_data/
+
+pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+```
+### Anaconda（方法三）
+此处提供本地配置、编译的详细步骤，例如：
+
+关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.hpccube.com/tool/)开发者社区下载安装。
+```
+DTK驱动:dtk24.04.3
+python:3.10
+torch:2.3.0
+flash-attn:2.6.1
+```
+`Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应`
+
+其它非深度学习库参照requirement.txt安装：
+```
+git clone http://developer.sourcefind.cn/codes/modelzoo/internvl2.5_pytorch.git
+
+cd /path/your_code_data/
+
+pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+```
+## 数据集
+
+无
+
+## 训练
+
+
+无
+
+### 单机多卡
+
+无
+
+## 推理
+
+### 单机多卡
+
+
+```
+python internvl_inference.py
+```
+
+
+## result
+
+- 多模态推理
+
+<div align=left>
+    <img src="./Pic/result.png"/>
+</div>
+
+
+
+### 精度
+
+无
+
+
+
+## 应用场景
+
+### 算法类别
+
+`对话问答`
+
+### 热点应用行业
+
+`科研,教育,政府,金融`
+
+## 预训练权重
+
+模型可在[SCNet](http://113.200.138.88:18080/aimodels/)进行搜索下载
+
+- [OpenGVLab/InternVL2_5模型下载SCNet链接](http://113.200.138.88:18080/aimodels/OpenGVLab/InternVL2_5)
+
+## 源码仓库及问题反馈
+- https://developer.sourcefind.cn/codes/modelzoo/internvl2.5_pytorch
+
+## 参考资料
+
+- https://modelscope.cn/models/OpenGVLab/InternVL2_5-8B
+- https://github.com/OpenGVLab/InternVL
+
+

internvl_inference.py

+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)
+
+import math
+import torch
+from transformers import AutoTokenizer, AutoModel
+
+def split_model(model_name):
+    device_map = {}
+    world_size = torch.cuda.device_count()
+    num_layers = {
+        'InternVL2_5-1B': 24, 'InternVL2_5-2B': 24, 'InternVL2_5-4B': 36, 'InternVL2_5-8B': 32,
+        'InternVL2_5-26B': 48, 'InternVL2_5-38B': 64, 'InternVL2_5-78B': 80}[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.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/InternVL2_5-8B"
+device_map = split_model('InternVL2_5-8B')
+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()
+
+
+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 = "/home/wanglch/InternVL2_5/InternVL2_5-8B/"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    use_flash_attn=True,
+    trust_remote_code=True).eval().cuda()
+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('/home/wanglch/InternVL2_5/InternVL2_5-8B/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('/home/wanglch/InternVL2_5/InternVL2_5-8B/examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
+pixel_values2 = load_image('/home/wanglch/InternVL2_5/InternVL2_5-8B/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('/home/wanglch/InternVL2_5/InternVL2_5-8B/examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
+pixel_values2 = load_image('/home/wanglch/InternVL2_5/InternVL2_5-8B/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('/home/wanglch/InternVL2_5/InternVL2_5-8B/examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
+pixel_values2 = load_image('/home/wanglch/InternVL2_5/InternVL2_5-8B/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 = '/home/wanglch/InternVL2_5/InternVL2_5-8B/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}')
+

model.properties

+# 模型唯一标识
+modelCode=1473
+# 模型名称
+modelName=InterVL2.5_pytorch
+# 模型描述
+modelDescription=高级多模态大型语言模型（MLLM）系列，它建立在InternVL 2.0的基础上，保持了其核心模型架构，同时引入了训练和测试策略以及数据质量的显著增强。
+# 应用场景
+appScenario=推理,训练,对话问答,科研,教育,政府,金融
+# 框架类型
+frameType=Pytorch

requirements.txt

+transformers>=4.37.2
+decord
+timm