vllm support

.gitattributes

@@ -34,4 +34,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 examples/red-panda.mp4 filter=lfs diff=lfs merge=lfs -text
-examples/image2.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,28 +1,17 @@
 ---
 license: mit
 pipeline_tag: image-text-to-text
-library_name: transformers
-base_model:
-  - OpenGVLab/InternViT-300M-448px
-  - internlm/internlm2_5-7b-chat
-new_version: OpenGVLab/InternVL2_5-8B
-base_model_relation: merge
-language:
-  - multilingual
-tags:
-  - internvl
-  - custom_code
 ---
 
 # InternVL2-8B
 
-[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL)  [\[📜 InternVL 1.0\]](https://huggingface.co/papers/2312.14238)  [\[📜 InternVL 1.5\]](https://huggingface.co/papers/2404.16821)  [\[📜 Mini-InternVL\]](https://arxiv.org/abs/2410.16261)  [\[📜 InternVL 2.5\]](https://huggingface.co/papers/2412.05271)
+[\[📂 GitHub\]](https://github.com/OpenGVLab/InternVL)  [\[🆕 Blog\]](https://internvl.github.io/blog/)  [\[📜 InternVL 1.0 Paper\]](https://arxiv.org/abs/2312.14238)  [\[📜 InternVL 1.5 Report\]](https://arxiv.org/abs/2404.16821)
 
-[\[🆕 Blog\]](https://internvl.github.io/blog/)  [\[🗨️ Chat Demo\]](https://internvl.opengvlab.com/)  [\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL)  [\[🚀 Quick Start\]](#quick-start)  [\[📖 Documents\]](https://internvl.readthedocs.io/en/latest/)
+[\[🗨️ Chat Demo\]](https://internvl.opengvlab.com/)  [\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL)  [\[🚀 Quick Start\]](#quick-start)  [\[📖 中文解读\]](https://zhuanlan.zhihu.com/p/706547971)  [\[📖 Documents\]](https://internvl.readthedocs.io/en/latest/)
 
-<div align="center">
-  <img width="500" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/64006c09330a45b03605bba3/zJsd2hqd3EevgXo6fNgC-.png">
-</div>
+[切换至中文版](#简介)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/_mLpMwsav5eMeNcZdrIQl.png)
 
 ## Introduction
 
@@ -62,7 +51,7 @@ InternVL 2.0 is a multimodal large language model series, featuring models of va
 |      MME<sub>sum</sub>       |        2024.6        |       2187.8       |    2210.3    |
 |         RealWorldQA          |         63.5         |        66.0        |     64.4     |
 |     AI2D<sub>test</sub>      |         78.4         |        80.7        |     83.8     |
-|      MMMU<sub>val</sub>      |         45.8         |        46.8        |     51.8     |
+|      MMMU<sub>val</sub>      |         45.8         |    45.2 / 46.8     | 49.3 / 51.8  |
 |  MMBench-EN<sub>test</sub>   |         77.2         |        82.2        |     81.7     |
 |  MMBench-CN<sub>test</sub>   |         74.2         |        82.0        |     81.2     |
 |    CCBench<sub>dev</sub>     |         45.9         |        69.8        |     75.9     |
@@ -73,9 +62,11 @@ InternVL 2.0 is a multimodal large language model series, featuring models of va
 | MathVista<sub>testmini</sub> |         54.3         |        53.5        |     58.3     |
 |  OpenCompass<sub>avg</sub>   |         58.8         |        61.7        |     64.1     |
 
-- For more details and evaluation reproduction, please refer to our [Evaluation Guide](https://internvl.readthedocs.io/en/latest/internvl2.0/evaluation.html).
+- We simultaneously use InternVL and VLMEvalKit repositories for model evaluation. Specifically, the results reported for DocVQA, ChartQA, InfoVQA, TextVQA, MME, AI2D, MMBench, CCBench, MMVet, and SEED-Image were tested using the InternVL repository. OCRBench, RealWorldQA, HallBench, and MathVista were evaluated using the VLMEvalKit.
+
+- For MMMU, we report both the original scores (left side: evaluated using the InternVL codebase for InternVL series models, and sourced from technical reports or webpages for other models) and the VLMEvalKit scores (right side: collected from the OpenCompass leaderboard).
 
-- We simultaneously use [InternVL](https://github.com/OpenGVLab/InternVL) and [VLMEvalKit](https://github.com/open-compass/VLMEvalKit) repositories for model evaluation. Specifically, the results reported for DocVQA, ChartQA, InfoVQA, TextVQA, MME, AI2D, MMBench, CCBench, MMVet (GPT-4-0613), and SEED-Image were tested using the InternVL repository. MMMU, OCRBench, RealWorldQA, HallBench, MMVet (GPT-4-Turbo), and MathVista were evaluated using the VLMEvalKit.
+- Please note that evaluating the same model using different testing toolkits like InternVL and VLMEvalKit 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.
 
 ### Video Benchmarks
 
@@ -113,11 +104,17 @@ InternVL 2.0 is a multimodal large language model series, featuring models of va
 
 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.
 
+### Invitation to Evaluate InternVL
+
+We welcome MLLM benchmark developers to assess our InternVL1.5 and InternVL2 series models. If you need to add your evaluation results here, please contact me at [wztxy89@163.com](mailto:wztxy89@163.com).
+
 ## Quick Start
 
-We provide an example code to run `InternVL2-8B` using `transformers`.
+We provide an example code to run InternVL2-8B using `transformers`.
 
-> Please use transformers>=4.37.2 to ensure the model works normally.
+We also welcome you to experience the InternVL2 series models in our [online demo](https://internvl.opengvlab.com/).
+
+> Please use transformers==4.37.2 to ensure the model works normally.
 
 ### Model Loading
 
@@ -131,7 +128,6 @@ model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
-    use_flash_attn=True,
     trust_remote_code=True).eval().cuda()
 ```
 
@@ -146,7 +142,20 @@ model = AutoModel.from_pretrained(
     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
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModel
+path = "OpenGVLab/InternVL2-8B"
+model = AutoModel.from_pretrained(
+    path,
+    torch_dtype=torch.bfloat16,
+    load_in_4bit=True,
+    low_cpu_mem_usage=True,
     trust_remote_code=True).eval()
 ```
 
@@ -180,7 +189,6 @@ def split_model(model_name):
     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
 
@@ -192,7 +200,6 @@ 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()
 ```
@@ -288,13 +295,12 @@ 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)
+generation_config = dict(max_new_tokens=1024, do_sample=False)
 
 # pure-text conversation (纯文本对话)
 question = 'Hello, who are you?'
@@ -409,13 +415,13 @@ response, history = model.chat(tokenizer, pixel_values, question, generation_con
                                num_patches_list=num_patches_list, history=None, return_history=True)
 print(f'User: {question}\nAssistant: {response}')
 
-question = 'Describe this video in detail.'
+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
+#### Streaming output
 
 Besides this method, you can also use the following code to get streamed output.
 
@@ -446,48 +452,56 @@ for new_text in streamer:
 
 ## Finetune
 
-Many repositories now support fine-tuning of the InternVL series models, including [InternVL](https://github.com/OpenGVLab/InternVL), [SWIFT](https://github.com/modelscope/ms-swift), [XTurner](https://github.com/InternLM/xtuner), and others. Please refer to their documentation for more details on fine-tuning.
+SWIFT from ModelScope community has supported the fine-tuning (Image/Video) of InternVL, please check [this link](https://github.com/modelscope/swift/blob/main/docs/source_en/Multi-Modal/internvl-best-practice.md) for more details.
 
 ## Deployment
 
 ### LMDeploy
 
-LMDeploy is a toolkit for compressing, deploying, and serving LLMs & VLMs.
+LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by the MMRazor and MMDeploy teams.
 
 ```sh
-pip install lmdeploy>=0.5.3
+pip install lmdeploy
 ```
 
 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
+#### A 'Hello, world' example
 
 ```python
-from lmdeploy import pipeline, TurbomindEngineConfig
+from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
 from lmdeploy.vl import load_image
 
 model = 'OpenGVLab/InternVL2-8B'
+system_prompt = '我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。'
 image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
+chat_template_config = ChatTemplateConfig('internvl-internlm2')
+chat_template_config.meta_instruction = system_prompt
+pipe = pipeline(model, chat_template_config=chat_template_config,
+                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
+#### 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.
 
 ```python
-from lmdeploy import pipeline, TurbomindEngineConfig
+from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
 from lmdeploy.vl import load_image
 from lmdeploy.vl.constants import IMAGE_TOKEN
 
 model = 'OpenGVLab/InternVL2-8B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
+system_prompt = '我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。'
+chat_template_config = ChatTemplateConfig('internvl-internlm2')
+chat_template_config.meta_instruction = system_prompt
+pipe = pipeline(model, chat_template_config=chat_template_config,
+                backend_config=TurbomindEngineConfig(session_len=8192))
 
 image_urls=[
     'https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg',
@@ -500,16 +514,20 @@ response = pipe((f'Image-1: {IMAGE_TOKEN}\nImage-2: {IMAGE_TOKEN}\ndescribe thes
 print(response.text)
 ```
 
-#### Batch Prompts Inference
+#### Batch prompts inference
 
 Conducting inference with batch prompts is quite straightforward; just place them within a list structure:
 
 ```python
-from lmdeploy import pipeline, TurbomindEngineConfig
+from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
 from lmdeploy.vl import load_image
 
 model = 'OpenGVLab/InternVL2-8B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
+system_prompt = '我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。'
+chat_template_config = ChatTemplateConfig('internvl-internlm2')
+chat_template_config.meta_instruction = system_prompt
+pipe = pipeline(model, chat_template_config=chat_template_config,
+                backend_config=TurbomindEngineConfig(session_len=8192))
 
 image_urls=[
     "https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/demo/resources/human-pose.jpg",
@@ -520,16 +538,20 @@ response = pipe(prompts)
 print(response)
 ```
 
-#### Multi-turn Conversation
+#### 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.
 
 ```python
-from lmdeploy import pipeline, TurbomindEngineConfig, GenerationConfig
+from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig, GenerationConfig
 from lmdeploy.vl import load_image
 
 model = 'OpenGVLab/InternVL2-8B'
-pipe = pipeline(model, backend_config=TurbomindEngineConfig(session_len=8192))
+system_prompt = '我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。'
+chat_template_config = ChatTemplateConfig('internvl-internlm2')
+chat_template_config.meta_instruction = system_prompt
+pipe = pipeline(model, chat_template_config=chat_template_config,
+                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)
@@ -541,10 +563,20 @@ print(sess.response.text)
 
 #### Service
 
+To deploy InternVL2 as an API, please configure the chat template config first. Create the following JSON file `chat_template.json`.
+
+```json
+{
+    "model_name":"internvl-internlm2",
+    "meta_instruction":"我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。",
+    "stop_words":["<|im_start|>", "<|im_end|>"]
+}
+```
+
 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:
 
 ```shell
-lmdeploy serve api_server OpenGVLab/InternVL2-8B --server-port 23333
+lmdeploy serve api_server OpenGVLab/InternVL2-8B --backend turbomind --server-port 23333 --chat-template chat_template.json
 ```
 
 To use the OpenAI-style interface, you need to install OpenAI:
@@ -581,26 +613,28 @@ response = client.chat.completions.create(
 print(response)
 ```
 
+### vLLM
+
+TODO
+
+### Ollama
+
+TODO
+
 ## License
 
-This project is released under the MIT License. This project uses the pre-trained internlm2_5-7b-chat as a component, which is licensed under the Apache License 2.0.
+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:
 
 ```BibTeX
-@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{gao2024mini,
-  title={Mini-internvl: A flexible-transfer pocket multimodal model with 5\% parameters and 90\% performance},
-  author={Gao, Zhangwei and Chen, Zhe and Cui, Erfei and Ren, Yiming and Wang, Weiyun and Zhu, Jinguo and Tian, Hao and Ye, Shenglong and He, Junjun and Zhu, Xizhou and others},
-  journal={arXiv preprint arXiv:2410.16261},
-  year={2024}
+@article{chen2023internvl,
+  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 Li, Bin and Luo, Ping and Lu, Tong and Qiao, Yu and Dai, Jifeng},
+  journal={arXiv preprint arXiv:2312.14238},
+  year={2023}
 }
 @article{chen2024far,
   title={How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites},
@@ -608,11 +642,300 @@ If you find this project useful in your research, please consider citing:
   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},
+```
+
+## 简介
+
+我们很高兴宣布 InternVL 2.0 的发布，这是 InternVL 系列多模态大语言模型的最新版本。InternVL 2.0 提供了多种**指令微调**的模型，参数从 10 亿到 1080 亿不等。此仓库包含经过指令微调的 InternVL2-8B 模型。
+
+与最先进的开源多模态大语言模型相比，InternVL 2.0 超越了大多数开源模型。它在各种能力上表现出与闭源商业模型相媲美的竞争力，包括文档和图表理解、信息图表问答、场景文本理解和 OCR 任务、科学和数学问题解决，以及文化理解和综合多模态能力。
+
+InternVL 2.0 使用 8k 上下文窗口进行训练，训练数据包含长文本、多图和视频数据，与 InternVL 1.5 相比，其处理这些类型输入的能力显著提高。更多详细信息，请参阅我们的博客和 GitHub。
+
+|       模型名称       |                                      视觉部分                                       |                                           语言部分                                           |                             HF 链接                              |                                MS 链接                                 |
+| :------------------: | :---------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------: | :--------------------------------------------------------------: | :--------------------------------------------------------------------: |
+|     InternVL2-1B     |    [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px)    |            [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct)            |     [🤗 link](https://huggingface.co/OpenGVLab/InternVL2-1B)     |     [🤖 link](https://modelscope.cn/models/OpenGVLab/InternVL2-1B)     |
+|     InternVL2-2B     |    [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px)    |          [internlm2-chat-1_8b](https://huggingface.co/internlm/internlm2-chat-1_8b)          |     [🤗 link](https://huggingface.co/OpenGVLab/InternVL2-2B)     |     [🤖 link](https://modelscope.cn/models/OpenGVLab/InternVL2-2B)     |
+|     InternVL2-4B     |    [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px)    |    [Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)     |     [🤗 link](https://huggingface.co/OpenGVLab/InternVL2-4B)     |     [🤖 link](https://modelscope.cn/models/OpenGVLab/InternVL2-4B)     |
+|     InternVL2-8B     |    [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px)    |          [internlm2_5-7b-chat](https://huggingface.co/internlm/internlm2_5-7b-chat)          |     [🤗 link](https://huggingface.co/OpenGVLab/InternVL2-8B)     |     [🤖 link](https://modelscope.cn/models/OpenGVLab/InternVL2-8B)     |
+|    InternVL2-26B     | [InternViT-6B-448px-V1-5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-5) |           [internlm2-chat-20b](https://huggingface.co/internlm/internlm2-chat-20b)           |    [🤗 link](https://huggingface.co/OpenGVLab/InternVL2-26B)     |    [🤖 link](https://modelscope.cn/models/OpenGVLab/InternVL2-26B)     |
+|    InternVL2-40B     | [InternViT-6B-448px-V1-5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-5) |       [Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B)       |    [🤗 link](https://huggingface.co/OpenGVLab/InternVL2-40B)     |    [🤖 link](https://modelscope.cn/models/OpenGVLab/InternVL2-40B)     |
+| InternVL2-Llama3-76B | [InternViT-6B-448px-V1-5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-5) | [Hermes-2-Theta-Llama-3-70B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-70B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B) | [🤖 link](https://modelscope.cn/models/OpenGVLab/InternVL2-Llama3-76B) |
+
+## 模型细节
+
+InternVL 2.0 是一个多模态大语言模型系列，包含各种规模的模型。对于每个规模的模型，我们都会发布针对多模态任务优化的指令微调模型。InternVL2-8B 包含 [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px)、一个 MLP 投影器和 [internlm2_5-7b-chat](https://huggingface.co/internlm/internlm2_5-7b-chat)。
+
+## 性能测试
+
+### 图像相关评测
+
+|          评测数据集          | MiniCPM-Llama3-V-2_5 | InternVL-Chat-V1-5 | InternVL2-8B |
+| :--------------------------: | :------------------: | :----------------: | :----------: |
+|           模型大小           |         8.5B         |       25.5B        |     8.1B     |
+|                              |                      |                    |              |
+|    DocVQA<sub>test</sub>     |         84.8         |        90.9        |     91.6     |
+|    ChartQA<sub>test</sub>    |          -           |        83.8        |     83.3     |
+|    InfoVQA<sub>test</sub>    |          -           |        72.5        |     74.8     |
+|    TextVQA<sub>val</sub>     |         76.6         |        80.6        |     77.4     |
+|           OCRBench           |         725          |        724         |     794      |
+|      MME<sub>sum</sub>       |        2024.6        |       2187.8       |    2210.3    |
+|         RealWorldQA          |         63.5         |        66.0        |     64.4     |
+|     AI2D<sub>test</sub>      |         78.4         |        80.7        |     83.8     |
+|      MMMU<sub>val</sub>      |         45.8         |    45.2 / 46.8     | 49.3 / 51.8  |
+|  MMBench-EN<sub>test</sub>   |         77.2         |        82.2        |     81.7     |
+|  MMBench-CN<sub>test</sub>   |         74.2         |        82.0        |     81.2     |
+|    CCBench<sub>dev</sub>     |         45.9         |        69.8        |     75.9     |
+|  MMVet<sub>GPT-4-0613</sub>  |          -           |        62.8        |     60.0     |
+| MMVet<sub>GPT-4-Turbo</sub>  |         52.8         |        55.4        |     54.2     |
+|          SEED-Image          |         72.3         |        76.0        |     76.2     |
+|   HallBench<sub>avg</sub>    |         42.4         |        49.3        |     45.2     |
+| MathVista<sub>testmini</sub> |         54.3         |        53.5        |     58.3     |
+|  OpenCompass<sub>avg</sub>   |         58.8         |        61.7        |     64.1     |
+
+- 我们同时使用 InternVL 和 VLMEvalKit 仓库进行模型评估。具体来说，DocVQA、ChartQA、InfoVQA、TextVQA、MME、AI2D、MMBench、CCBench、MMVet 和 SEED-Image 的结果是使用 InternVL 仓库测试的。OCRBench、RealWorldQA、HallBench 和 MathVista 是使用 VLMEvalKit 进行评估的。
+
+- 对于MMMU，我们报告了原始分数（左侧：InternVL系列模型使用InternVL代码库评测，其他模型的分数来自其技术报告或网页）和VLMEvalKit分数（右侧：从OpenCompass排行榜收集）。
+
+- 请注意，使用不同的测试工具包（如 InternVL 和 VLMEvalKit）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。
+
+### 视频相关评测
+
+|         评测数据集          | VideoChat2-HD-Mistral | Video-CCAM-9B | InternVL2-4B | InternVL2-8B |
+| :-------------------------: | :-------------------: | :-----------: | :----------: | :----------: |
+|          模型大小           |          7B           |      9B       |     4.2B     |     8.1B     |
+|                             |                       |               |              |              |
+|           MVBench           |         60.4          |     60.7      |     63.7     |     66.4     |
+| MMBench-Video<sub>8f</sub>  |           -           |       -       |     1.10     |     1.19     |
+| MMBench-Video<sub>16f</sub> |           -           |       -       |     1.18     |     1.28     |
+|    Video-MME<br>w/o subs    |         42.3          |     50.6      |     51.4     |     54.0     |
+|     Video-MME<br>w subs     |         54.6          |     54.9      |     53.4     |     56.9     |
+
+- 我们通过从每个视频中提取 16 帧来评估我们的模型在 MVBench 和 Video-MME 上的性能，每个视频帧被调整为 448x448 的图像。
+
+### 定位相关评测
+
+|              模型              | avg. | RefCOCO<br>(val) | RefCOCO<br>(testA) | RefCOCO<br>(testB) | RefCOCO+<br>(val) | RefCOCO+<br>(testA) | RefCOCO+<br>(testB) | RefCOCO‑g<br>(val) | RefCOCO‑g<br>(test) |
+| :----------------------------: | :--: | :--------------: | :----------------: | :----------------: | :---------------: | :-----------------: | :-----------------: | :----------------: | :-----------------: |
+| UNINEXT-H<br>(Specialist SOTA) | 88.9 |       92.6       |        94.3        |        91.5        |       85.2        |        89.6         |        79.8         |        88.7        |        89.4         |
+|                                |      |                  |                    |                    |                   |                     |                     |                    |                     |
+| Mini-InternVL-<br>Chat-2B-V1-5 | 75.8 |       80.7       |        86.7        |        72.9        |       72.5        |        82.3         |        60.8         |        75.6        |        74.9         |
+| Mini-InternVL-<br>Chat-4B-V1-5 | 84.4 |       88.0       |        91.4        |        83.5        |       81.5        |        87.4         |        73.8         |        84.7        |        84.6         |
+|       InternVL‑Chat‑V1‑5       | 88.8 |       91.4       |        93.7        |        87.1        |       87.0        |        92.3         |        80.9         |        88.5        |        89.3         |
+|                                |      |                  |                    |                    |                   |                     |                     |                    |                     |
+|          InternVL2‑1B          | 79.9 |       83.6       |        88.7        |        79.8        |       76.0        |        83.6         |        67.7         |        80.2        |        79.9         |
+|          InternVL2‑2B          | 77.7 |       82.3       |        88.2        |        75.9        |       73.5        |        82.8         |        63.3         |        77.6        |        78.3         |
+|          InternVL2‑4B          | 84.4 |       88.5       |        91.2        |        83.9        |       81.2        |        87.2         |        73.8         |        84.6        |        84.6         |
+|          InternVL2‑8B          | 82.9 |       87.1       |        91.1        |        80.7        |       79.8        |        87.9         |        71.4         |        82.7        |        82.7         |
+|         InternVL2‑26B          | 88.5 |       91.2       |        93.3        |        87.4        |       86.8        |        91.0         |        81.2         |        88.5        |        88.6         |
+|         InternVL2‑40B          | 90.3 |       93.0       |        94.7        |        89.2        |       88.5        |        92.8         |        83.6         |        90.3        |        90.6         |
+|    InternVL2-<br>Llama3‑76B    | 90.0 |       92.2       |        94.8        |        88.4        |       88.8        |        93.1         |        82.8         |        89.5        |        90.3         |
+
+- 我们使用以下 Prompt 来评测 InternVL 的 Grounding 能力: `Please provide the bounding box coordinates of the region this sentence describes: <ref>{}</ref>`
+
+限制：尽管在训练过程中我们非常注重模型的安全性，尽力促使模型输出符合伦理和法律要求的文本，但受限于模型大小以及概率生成范式，模型可能会产生各种不符合预期的输出，例如回复内容包含偏见、歧视等有害内容，请勿传播这些内容。由于传播不良信息导致的任何后果，本项目不承担责任。
+
+### 邀请评测 InternVL
+
+我们欢迎各位 MLLM benchmark 的开发者对我们的 InternVL1.5 以及 InternVL2 系列模型进行评测。如果需要在此处添加评测结果，请与我联系（[wztxy89@163.com](mailto:wztxy89@163.com)）。
+
+## 快速启动
+
+我们提供了一个示例代码，用于使用 `transformers` 运行 InternVL2-8B。
+
+我们也欢迎你在我们的[在线demo](https://internvl.opengvlab.com/)中体验InternVL2的系列模型。
+
+> 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](#quick-start)。
+
+## 微调
+
+来自ModelScope社区的SWIFT已经支持对InternVL进行微调（图像/视频），详情请查看[此链接](https://github.com/modelscope/swift/blob/main/docs/source_en/Multi-Modal/internvl-best-practice.md)。
+
+## 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。
+
+```sh
+pip install lmdeploy
+```
+
+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
+
+```python
+from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
+from lmdeploy.vl import load_image
+
+model = 'OpenGVLab/InternVL2-8B'
+system_prompt = '我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。'
+image = load_image('https://raw.githubusercontent.com/open-mmlab/mmdeploy/main/tests/data/tiger.jpeg')
+chat_template_config = ChatTemplateConfig('internvl-internlm2')
+chat_template_config.meta_instruction = system_prompt
+pipe = pipeline(model, chat_template_config=chat_template_config,
+                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。
+
+```python
+from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
+from lmdeploy.vl import load_image
+from lmdeploy.vl.constants import IMAGE_TOKEN
+
+model = 'OpenGVLab/InternVL2-8B'
+system_prompt = '我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。'
+chat_template_config = ChatTemplateConfig('internvl-internlm2')
+chat_template_config.meta_instruction = system_prompt
+pipe = pipeline(model, chat_template_config=chat_template_config,
+                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]
+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：
+
+```python
+from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig
+from lmdeploy.vl import load_image
+
+model = 'OpenGVLab/InternVL2-8B'
+system_prompt = '我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。'
+chat_template_config = ChatTemplateConfig('internvl-internlm2')
+chat_template_config.meta_instruction = system_prompt
+pipe = pipeline(model, chat_template_config=chat_template_config,
+                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。
+
+```python
+from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig, GenerationConfig
+from lmdeploy.vl import load_image
+
+model = 'OpenGVLab/InternVL2-8B'
+system_prompt = '我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。'
+chat_template_config = ChatTemplateConfig('internvl-internlm2')
+chat_template_config.meta_instruction = system_prompt
+pipe = pipeline(model, chat_template_config=chat_template_config,
+                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
+
+为了将InternVL2部署成API，请先配置聊天模板配置文件。创建如下的 JSON 文件 `chat_template.json`。
+
+```json
+{
+    "model_name":"internvl-internlm2",
+    "meta_instruction":"我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。",
+    "stop_words":["<|im_start|>", "<|im_end|>"]
+}
+```
+
+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：
+
+```shell
+lmdeploy serve api_server OpenGVLab/InternVL2-8B --backend turbomind --server-port 23333 --chat-template chat_template.json
+```
+
+为了使用OpenAI风格的API接口，您需要安装OpenAI:
+
+```shell
+pip install openai
+```
+
+然后，使用下面的代码进行API调用:
+
+```python
+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)
+```
+
+### vLLM
+
+TODO
+
+### Ollama
+
+TODO
+
+## 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：
+
+```BibTeX
+@article{chen2023internvl,
+  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 Li, Bin and Luo, Ping and Lu, Tong and Qiao, Yu and Dai, Jifeng},
+  journal={arXiv preprint arXiv:2312.14238},
+  year={2023}
+}
+@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}
 }
 ```

configuration_intern_vit.py

@@ -3,7 +3,6 @@
 # Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
-
 import os
 from typing import Union
 

configuration_internvl_chat.py

@@ -39,20 +39,20 @@ class InternVLChatConfig(PretrainedConfig):
         super().__init__(**kwargs)
 
         if vision_config is None:
-            vision_config = {'architectures': ['InternVisionModel']}
+            vision_config = {}
             logger.info('vision_config is None. Initializing the InternVisionConfig with default values.')
 
         if llm_config is None:
-            llm_config = {'architectures': ['InternLM2ForCausalLM']}
+            llm_config = {}
             logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
 
         self.vision_config = InternVisionConfig(**vision_config)
-        if llm_config.get('architectures')[0] == 'LlamaForCausalLM':
+        if llm_config['architectures'][0] == 'LlamaForCausalLM':
             self.llm_config = LlamaConfig(**llm_config)
-        elif llm_config.get('architectures')[0] == 'InternLM2ForCausalLM':
+        elif llm_config['architectures'][0] == 'InternLM2ForCausalLM':
             self.llm_config = InternLM2Config(**llm_config)
         else:
-            raise ValueError('Unsupported architecture: {}'.format(llm_config.get('architectures')[0]))
+            raise ValueError('Unsupported architecture: {}'.format(llm_config['architectures'][0]))
         self.use_backbone_lora = use_backbone_lora
         self.use_llm_lora = use_llm_lora
         self.select_layer = select_layer

conversation.py

@@ -3,13 +3,11 @@ Conversation prompt templates.
 
 We kindly request that you import fastchat instead of copying this file if you wish to use it.
 If you have changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
-
-Modified from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py
 """
 
 import dataclasses
 from enum import IntEnum, auto
-from typing import Dict, List, Tuple, Union
+from typing import Any, Dict, List, Tuple, Union
 
 
 class SeparatorStyle(IntEnum):
@@ -346,6 +344,12 @@ register_conv_template(
         roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
         sep_style=SeparatorStyle.MPT,
         sep='<|im_end|>',
+        stop_token_ids=[
+            2,
+            6,
+            7,
+            8,
+        ],
         stop_str='<|endoftext|>',
     )
 )
@@ -361,6 +365,11 @@ register_conv_template(
         roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
         sep_style=SeparatorStyle.MPT,
         sep='<|im_end|>',
+        stop_token_ids=[
+            2,
+            92543,
+            92542
+        ]
     )
 )
 
@@ -375,17 +384,10 @@ register_conv_template(
         roles=('<|user|>\n', '<|assistant|>\n'),
         sep_style=SeparatorStyle.MPT,
         sep='<|end|>',
-    )
-)
-
-
-register_conv_template(
-    Conversation(
-        name='internvl2_5',
-        system_template='<|im_start|>system\n{system_message}',
-        system_message='你是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
-        roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
-        sep_style=SeparatorStyle.MPT,
-        sep='<|im_end|>\n',
+        stop_token_ids=[
+            2,
+            32000,
+            32007
+        ]
     )
 )

eval_llm_benchmark.log

@@ -1,53 +0,0 @@
-/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl_eval/lib/python3.10/site-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
-  warn("The installed version of bitsandbytes was compiled without GPU support. "
-/mnt/petrelfs/wangweiyun/miniconda3/envs/internvl_eval/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32
-model path is /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B
-09/30 19:08:03 - OpenCompass - WARNING - No previous results to reuse!
-09/30 19:08:03 - OpenCompass - INFO - Reusing experiements from 20240930_190803
-09/30 19:08:03 - OpenCompass - INFO - Current exp folder: /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B/20240930_190803
-09/30 19:08:06 - OpenCompass - INFO - Partitioned into 64 tasks.
-[                                                  ] 0/64, elapsed: 0s, ETA:
-09/30 19:52:33 - OpenCompass - INFO - Partitioned into 287 tasks.
-[                                                  ] 0/287, elapsed: 0s, ETA:
-dataset                       version    metric                        mode    internvl-chat-20b
-----------------------------  ---------  ----------------------------  ------  -------------------
-mmlu                          -          naive_average                 gen     73.17
-cmmlu                         -          naive_average                 gen     79.21
-ceval                         -          naive_average                 gen     80.14
-agieval                       -          -                             -       -
-GaokaoBench                   -          weighted_average              gen     74.99
-triviaqa                      2121ce     score                         gen     62.03
-triviaqa_wiki_1shot           -          -                             -       -
-nq                            3dcea1     score                         gen     28.12
-C3                            8c358f     accuracy                      gen     94.19
-race-high                     9a54b6     accuracy                      gen     90.82
-flores_100                    -          -                             -       -
-winogrande                    b36770     accuracy                      gen     85.87
-hellaswag                     e42710     accuracy                      gen     94.91
-bbh                           -          naive_average                 gen     72.67
-gsm8k                         1d7fe4     accuracy                      gen     75.59
-math                          393424     accuracy                      gen     39.50
-TheoremQA                     6f0af8     score                         gen     15.62
-MathBench                     -          -                             -       -
-openai_humaneval              8e312c     humaneval_pass@1              gen     69.51
-humanevalx                    -          -                             -       -
-sanitized_mbpp                a447ff     score                         gen     58.75
-mbpp_cn                       6fb572     score                         gen     48.20
-leval                         -          -                             -       -
-leval_closed                  -          -                             -       -
-leval_open                    -          -                             -       -
-longbench                     -          -                             -       -
-longbench_single-document-qa  -          -                             -       -
-longbench_multi-document-qa   -          -                             -       -
-longbench_summarization       -          -                             -       -
-longbench_few-shot-learning   -          -                             -       -
-longbench_synthetic-tasks     -          -                             -       -
-longbench_code-completion     -          -                             -       -
-teval                         -          -                             -       -
-teval_zh                      -          -                             -       -
-IFEval                        3321a3     Prompt-level-strict-accuracy  gen     52.31
-IFEval                        3321a3     Inst-level-strict-accuracy    gen     62.71
-IFEval                        3321a3     Prompt-level-loose-accuracy   gen     54.90
-IFEval                        3321a3     Inst-level-loose-accuracy     gen     64.87
-09/30 19:55:16 - OpenCompass - INFO - write summary to /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B/20240930_190803/summary/summary_20240930_190803.txt
-09/30 19:55:16 - OpenCompass - INFO - write csv to /mnt/petrelfs/wangweiyun/workspace_cz/InternVL/internvl_chat_dev/share_internvl/InternVL2-8B/20240930_190803/summary/summary_20240930_190803.csv

generation_config.json

@@ -1,8 +1,4 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.37.2",
-  "eos_token_id": [
-    92542,
-    92543
-  ]
+  "transformers_version": "4.37.2"
 }

modeling_intern_vit.py

@@ -3,7 +3,6 @@
 # Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
-
 from typing import Optional, Tuple, Union
 
 import torch
@@ -21,12 +20,18 @@ from transformers.utils import logging
 from .configuration_intern_vit import InternVisionConfig
 
 try:
+    try:  # v1
+        from flash_attn.flash_attn_interface import \
+            flash_attn_unpadded_qkvpacked_func
+    except:  # v2
+        from flash_attn.flash_attn_interface import \
+            flash_attn_varlen_qkvpacked_func as flash_attn_unpadded_qkvpacked_func
+
     from flash_attn.bert_padding import pad_input, unpad_input
-    from flash_attn.flash_attn_interface import \
-        flash_attn_varlen_qkvpacked_func
+
     has_flash_attn = True
 except:
-    print('FlashAttention2 is not installed.')
+    print('FlashAttention is not installed.')
     has_flash_attn = False
 
 logger = logging.get_logger(__name__)
@@ -69,7 +74,7 @@ class FlashAttention(nn.Module):
                 max_s = seqlen
                 cu_seqlens = torch.arange(0, (batch_size + 1) * seqlen, step=seqlen, dtype=torch.int32,
                                           device=qkv.device)
-                output = flash_attn_varlen_qkvpacked_func(
+                output = flash_attn_unpadded_qkvpacked_func(
                     qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
                     softmax_scale=self.softmax_scale, causal=causal
                 )
@@ -79,7 +84,7 @@ class FlashAttention(nn.Module):
                 x = rearrange(qkv, 'b s three h d -> b s (three h d)')
                 x_unpad, indices, cu_seqlens, max_s = unpad_input(x, key_padding_mask)
                 x_unpad = rearrange(x_unpad, 'nnz (three h d) -> nnz three h d', three=3, h=nheads)
-                output_unpad = flash_attn_varlen_qkvpacked_func(
+                output_unpad = flash_attn_unpadded_qkvpacked_func(
                     x_unpad, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
                     softmax_scale=self.softmax_scale, causal=causal
                 )
@@ -88,7 +93,7 @@ class FlashAttention(nn.Module):
                                    'b s (h d) -> b s h d', h=nheads)
         else:
             assert max_s is not None
-            output = flash_attn_varlen_qkvpacked_func(
+            output = flash_attn_unpadded_qkvpacked_func(
                 qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
                 softmax_scale=self.softmax_scale, causal=causal
             )
@@ -288,9 +293,9 @@ class InternVisionEncoderLayer(nn.Module):
         Args:
             hidden_states (`Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]`): input to the layer of shape `(batch, seq_len, embed_dim)`
         """
-        hidden_states = hidden_states + self.drop_path1(self.attn(self.norm1(hidden_states).to(hidden_states.dtype)) * self.ls1)
+        hidden_states = hidden_states + self.drop_path1(self.attn(self.norm1(hidden_states)) * self.ls1)
 
-        hidden_states = hidden_states + self.drop_path2(self.mlp(self.norm2(hidden_states).to(hidden_states.dtype)) * self.ls2)
+        hidden_states = hidden_states + self.drop_path2(self.mlp(self.norm2(hidden_states)) * self.ls2)
 
         return hidden_states
 

modeling_internvl_chat.py

@@ -3,9 +3,8 @@
 # Copyright (c) 2024 OpenGVLab
 # Licensed under The MIT License [see LICENSE for details]
 # --------------------------------------------------------
-
 import warnings
-from typing import List, Optional, Tuple, Union
+from typing import Any, List, Optional, Tuple, Union
 
 import torch.utils.checkpoint
 import transformers
@@ -19,7 +18,7 @@ from transformers.utils import ModelOutput, logging
 
 from .configuration_internvl_chat import InternVLChatConfig
 from .conversation import get_conv_template
-from .modeling_intern_vit import InternVisionModel, has_flash_attn
+from .modeling_intern_vit import InternVisionModel
 from .modeling_internlm2 import InternLM2ForCausalLM
 
 logger = logging.get_logger(__name__)
@@ -36,14 +35,13 @@ def version_cmp(v1, v2, op='eq'):
 class InternVLChatModel(PreTrainedModel):
     config_class = InternVLChatConfig
     main_input_name = 'pixel_values'
-    base_model_prefix = 'language_model'
     _supports_flash_attn_2 = True
     _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'InternLM2DecoderLayer']
 
-    def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None, use_flash_attn=True):
+    def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None):
         super().__init__(config)
 
-        assert version_cmp(transformers.__version__, '4.37.0', 'ge')
+        assert version_cmp(transformers.__version__, '4.36.2', 'ge')
         image_size = config.force_image_size or config.vision_config.image_size
         patch_size = config.vision_config.patch_size
         self.patch_size = patch_size
@@ -52,9 +50,6 @@ class InternVLChatModel(PreTrainedModel):
         self.num_image_token = int((image_size // patch_size) ** 2 * (config.downsample_ratio ** 2))
         self.downsample_ratio = config.downsample_ratio
         self.ps_version = config.ps_version
-        use_flash_attn = use_flash_attn if has_flash_attn else False
-        config.vision_config.use_flash_attn = True if use_flash_attn else False
-        config.llm_config.attn_implementation = 'flash_attention_2' if use_flash_attn else 'eager'
 
         logger.info(f'num_image_token: {self.num_image_token}')
         logger.info(f'ps_version: {self.ps_version}')
@@ -103,7 +98,7 @@ class InternVLChatModel(PreTrainedModel):
         return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
         image_flags = image_flags.squeeze(-1)
-        input_embeds = self.language_model.get_input_embeddings()(input_ids).clone()
+        input_embeds = self.language_model.get_input_embeddings()(input_ids)
 
         vit_embeds = self.extract_feature(pixel_values)
         vit_embeds = vit_embeds[image_flags == 1]
@@ -112,7 +107,7 @@ class InternVLChatModel(PreTrainedModel):
         B, N, C = input_embeds.shape
         input_embeds = input_embeds.reshape(B * N, C)
 
-        if torch.distributed.is_initialized() and torch.distributed.get_rank() == 0:
+        if torch.distributed.get_rank() == 0:
             print(f'dynamic ViT batch size: {vit_batch_size}, images per sample: {vit_batch_size / B}, dynamic token length: {N}')
 
         input_ids = input_ids.reshape(B * N)
@@ -236,9 +231,9 @@ class InternVLChatModel(PreTrainedModel):
 
         tokenizer.padding_side = 'left'
         model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
-        input_ids = model_inputs['input_ids'].to(self.device)
-        attention_mask = model_inputs['attention_mask'].to(self.device)
-        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep.strip())
+        input_ids = model_inputs['input_ids'].cuda()
+        attention_mask = model_inputs['attention_mask'].cuda()
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             pixel_values=pixel_values,
@@ -247,7 +242,7 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         responses = tokenizer.batch_decode(generation_output, skip_special_tokens=True)
-        responses = [response.split(template.sep.strip())[0].strip() for response in responses]
+        responses = [response.split(template.sep)[0].strip() for response in responses]
         return responses
 
     def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
@@ -266,7 +261,7 @@ class InternVLChatModel(PreTrainedModel):
 
         template = get_conv_template(self.template)
         template.system_message = self.system_message
-        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep.strip())
+        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
 
         history = [] if history is None else history
         for (old_question, old_answer) in history:
@@ -285,8 +280,8 @@ class InternVLChatModel(PreTrainedModel):
             query = query.replace('<image>', image_tokens, 1)
 
         model_inputs = tokenizer(query, return_tensors='pt')
-        input_ids = model_inputs['input_ids'].to(self.device)
-        attention_mask = model_inputs['attention_mask'].to(self.device)
+        input_ids = model_inputs['input_ids'].cuda()
+        attention_mask = model_inputs['attention_mask'].cuda()
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             pixel_values=pixel_values,
@@ -295,7 +290,7 @@ class InternVLChatModel(PreTrainedModel):
             **generation_config
         )
         response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
-        response = response.split(template.sep.strip())[0].strip()
+        response = response.split(template.sep)[0].strip()
         history.append((question, response))
         if return_history:
             return response, history
@@ -315,6 +310,7 @@ class InternVLChatModel(PreTrainedModel):
             visual_features: Optional[torch.FloatTensor] = None,
             generation_config: Optional[GenerationConfig] = None,
             output_hidden_states: Optional[bool] = None,
+            return_dict: Optional[bool] = None,
             **generate_kwargs,
     ) -> torch.LongTensor:
 
@@ -342,6 +338,7 @@ class InternVLChatModel(PreTrainedModel):
             attention_mask=attention_mask,
             generation_config=generation_config,
             output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
             use_cache=True,
             **generate_kwargs,
         )