update readme

Author: yiranyyu

README.md

@@ -16,17 +16,16 @@
 </div>
 
 
-**MiniCPM-V** is a series of end-side multimodal LLMs designed for image-text understanding. These models accept image and text inputs and provide high-quality text outputs. Since February 2024, we have released four versions of the model, aiming to achieve **strong performance and efficient deployment**. The most noteworthy models in this series currently include:
+**MiniCPM-V** is a series of end-side multimodal LLMs (MLLMs) designed for vision-language understanding. Models take image and text as inputs and provide high-quality text outputs. Since February 2024, we have released 4 versions of the model, aiming to achieve **strong performance and efficient deployment**! The most noteworthy models in this series currently include:
 
-- **MiniCPM-Llama3-V 2.5**: 🔥🔥🔥 The latest and most capable model in the MiniCPM-V series. With a total of 8B parameters, the model surpasses proprietary models such as GPT-4V-1106, Gemini Pro, Qwen-VL-Max and Claude 3 in overall performance. Its OCR capability and instruction-following capability have been further enhanced. The model supports multimodal interaction in over 30 languages including English, Chinese, French, Spanish, German etc. Equipped with model quantization and efficient inference technologies on CPUs, NPUs and compilation optimizations, MiniCPM-Llama3-V 2.5 can be efficiently deployed on edge devices.
+- **MiniCPM-Llama3-V 2.5**: 🔥🔥🔥 The latest and most capable model in the MiniCPM-V series. With a total of 8B parameters, the model surpasses proprietary models such as GPT-4V-1106, Gemini Pro, Qwen-VL-Max and Claude 3 in overall performance. Equipped with the enhanced OCR and instruction-following capability, the model can also support multimodal conversation for over 30 languages including English, Chinese, French, Spanish, German etc. With help of quantization, compilation optimizations, and several efficient inference technologies on CPUs and NPUs, MiniCPM-Llama3-V 2.5 can be efficiently deployed on end-side devices.
 
-- **MiniCPM-V 2.0**: The lightest model in the MiniCPM-V series. With 2B parameters, it surpasses larger-scale models such as Yi-VL 34B, CogVLM-Chat 17B, and Qwen-VL-Chat 10B in overall performance. It accepts image inputs of any aspect ratio up to 1.8 million pixels (e.g., 1344x1344), achieving comparable performance with Gemini Pro in understanding scene-text and matches GPT-4V in preventing hallucinations.
+- **MiniCPM-V 2.0**: The lightest model in the MiniCPM-V series. With 2B parameters, it surpasses larger models such as Yi-VL 34B, CogVLM-Chat 17B, and Qwen-VL-Chat 10B in overall performance. It can accept image inputs of any aspect ratio and up to 1.8 million pixels (e.g., 1344x1344), achieving comparable performance with Gemini Pro in understanding scene-text and matches GPT-4V in low hallucination rates.
 
 
 ## News <!-- omit in toc -->
 
-<!-- * [2024.05.22] We further improved the inference efficiency on edge-side devices, providing a speed of 6-8 tokens/s, try it now! -->
-* [2024.05.20] We open-soure MiniCPM-Llama3-V 2.5, it has improved OCR capability and supports 30+ languages, representing the first edge-side multimodal LLM achieving GPT-4V level performance! We provide [efficient inference](#deployment-on-mobile-phone) and [simple fine-tuning](./finetune/readme.md), try it now!
+* [2024.05.20] We open-soure MiniCPM-Llama3-V 2.5, it has improved OCR capability and supports 30+ languages, representing the first edge-side MLLM achieving GPT-4V level performance! We provide [efficient inference](#deployment-on-mobile-phone) and [simple fine-tuning](./finetune/readme.md). Try it now!
 * [2024.04.23] MiniCPM-V-2.0 supports vLLM now! Click [here](#vllm) to view more details.
 * [2024.04.18] We create a HuggingFace Space to host the demo of MiniCPM-V 2.0 at [here](https://huggingface.co/spaces/openbmb/MiniCPM-V-2)!
 * [2024.04.17] MiniCPM-V-2.0 supports deploying [WebUI Demo](#webui-demo) now!
@@ -45,6 +44,7 @@
 - [Online Demo](#online-demo)
 - [Install](#install)
 - [Inference](#inference)
+  - [Hardware Requirements](#hardware-requirements)
   - [Model Zoo](#model-zoo)
   - [Multi-turn Conversation](#multi-turn-conversation)
   - [Inference on Mac](#inference-on-mac)
@@ -60,19 +60,19 @@
 **MiniCPM-Llama3-V 2.5** is the latest model in the MiniCPM-V series. The model is built on SigLip-400M and Llama3-8B-Instruct with a total of 8B parameters. It exhibits a significant performance improvement over MiniCPM-V 2.0. Notable features of MiniCPM-Llama3-V 2.5 include:
 
 - 🔥 **Leading Performance.**
-  MiniCPM-Llama3-V 2.5 has achieved an average score of 65.1 on OpenCompass, a comprehensive evaluation over 11 popular benchmarks. **It surpasses widely used proprietary models like GPT-4V-1106, Gemini Pro, Claude 3 and Qwen-VL-Max with 8B parameters**, greatly outperforming other multimodal LLMs built on Llama 3.
+  MiniCPM-Llama3-V 2.5 has achieved an average score of 65.1 on OpenCompass, a comprehensive evaluation over 11 popular benchmarks. **With only 8B parameters, it surpasses widely used proprietary models like GPT-4V-1106, Gemini Pro, Claude 3 and Qwen-VL-Max** and greatly outperforms other Llama 3-based MLLMs.
 
 - 💪 **Strong OCR Capabilities.**
-  MiniCPM-Llama3-V 2.5 can process images with any aspect ratio up to 1.8 million pixels, achieving an **700+ score on OCRBench, surpassing proprietary models such as GPT-4o, GPT-4V-0409, Qwen-VL-Max and Gemini Pro**. Based on recent user feedback, MiniCPM-Llama3-V 2.5 has now enhanced full-text OCR extraction, table-to-markdown conversion, and other high-utility capabilities, and has further strengthened its instruction-following and complex reasoning abilities, enhancing multimodal interaction experiences.
+  MiniCPM-Llama3-V 2.5 can process images with any aspect ratio and up to 1.8 million pixels (e.g., 1344x1344), achieving an **700+ score on OCRBench, surpassing proprietary models such as GPT-4o, GPT-4V-0409, Qwen-VL-Max and Gemini Pro**. Based on recent user feedback, MiniCPM-Llama3-V 2.5 has now enhanced full-text OCR extraction, table-to-markdown conversion, and other high-utility capabilities, and has further strengthened its instruction-following and complex reasoning abilities, enhancing multimodal interaction experiences.
 
 - 🏆 **Trustworthy Behavior.**
-  Leveraging the latest [RLAIF-V](https://github.com/RLHF-V/RLAIF-V/) method (the newest technology in the [RLHF-V](https://github.com/RLHF-V) [CVPR'24] series), MiniCPM-Llama3-V 2.5 exhibits trustworthy multimodal behavior. It achieves **10.3%** hallucination rate on Object HalBench, lower than GPT-4V-1106 (13.6%), achieving the best level within the open-source community.
+  Leveraging the latest [RLAIF-V](https://github.com/RLHF-V/RLAIF-V/) method (the newest technology in the [RLHF-V](https://github.com/RLHF-V) [CVPR'24] series), MiniCPM-Llama3-V 2.5 exhibits more trustworthy behavior. It achieves **10.3%** hallucination rate on Object HalBench, lower than GPT-4V-1106 (13.6%), achieving the best-level performance within the open-source community.
 
 - 🌏 **Multilingual Support.**
-  Thanks to the strong multilingual capabilities of Llama 3 and the cross-lingual generalization technique from [VisCPM](https://github.com/OpenBMB/VisCPM), MiniCPM-Llama3-V 2.5 extends its foundational bilingual (Chinese-English) multimodal capabilities to support **30+ languages including German, French, Spanish, Italian, Russian etc.** We achieve this extension through only minimal instruction-tuning with translated multimodal data. [All Supported Languages](./assets/minicpm-llama-v-2-5_languages.md).
+  Thanks to the strong multilingual capabilities of Llama 3 and the cross-lingual generalization technique from [VisCPM](https://github.com/OpenBMB/VisCPM), MiniCPM-Llama3-V 2.5 extends its bilingual (Chinese-English) multimodal capabilities to **over 30 languages including German, French, Spanish, Italian, Russian etc.** We achieve this extension through only 90k translated multimodal data (<0.5% SFT data). [All Supported Languages](./assets/minicpm-llama-v-2-5_languages.md).
 
 - 🚀 **Efficient Deployment.**
-  MiniCPM-Llama3-V 2.5 systematically employs **model quantization, CPU optimizations, NPU optimizations and compilation optimizations** as acceleration techniques, achieving high-efficiency deployment on edge devices. For mobile phones with Qualcomm chips, we have integrated the NPU acceleration framework QNN into llama.cpp for the first time. After systematic optimization, MiniCPM-Llama3-V 2.5 has realized a **150-fold acceleration in multimodal large model edge-side image encoding** and a **3-fold increase in language decoding speed**.
+  MiniCPM-Llama3-V 2.5 systematically employs **model quantization, CPU optimizations, NPU optimizations and compilation optimizations**, achieving high-efficiency deployment on edge devices. For mobile phones with Qualcomm chips, we have integrated the NPU acceleration framework QNN into llama.cpp for the first time. After systematic optimization, MiniCPM-Llama3-V 2.5 has realized a **150-fold acceleration in multimodal large model edge-side image encoding** and a **3-fold increase in language decoding speed**.
 
 ### Evaluation <!-- omit in toc -->
 
@@ -454,6 +454,15 @@ pip install -r requirements.txt
 
 ## Inference
 
+### Hardware Requirements
+
+| Model                | GPU Memory        |
+|:----------------------|:-------------------:|
+| MiniCPM-Llama3-V 2.5  | 19 GB   |
+| MiniCPM-Llama3-V 2.5 (int4)  | 8 GB |
+| MiniCPM-Llama3-V 2.0  | 8 GB |
+
+
 ### Model Zoo
 | Model                | Description       | Download Link |
 |:----------------------|:-------------------|:---------------:|
@@ -463,7 +472,7 @@ pip install -r requirements.txt
 | MiniCPM-V 1.0 | Lightest version, achieving the fastest inference. |   [🤗](https://huggingface.co/openbmb/MiniCPM-V) &nbsp;&nbsp; [<img src="./assets/modelscope_logo.png" width="20px"></img>](https://modelscope.cn/models/OpenBMB/MiniCPM-V) |
 
 ### Multi-turn Conversation
-Please refer to the following codes to run `MiniCPM-V`
+Please refer to the following codes to run `MiniCPM-V` and `OmniLMM`.
 
 <div align="center">
 <img src="assets/airplane.jpeg" width="500px">
@@ -590,13 +599,13 @@ python examples/minicpmv_example.py
 
 ### Simple Fine-tuning <!-- omit in toc -->
 
-We supports simple fine-tuning with Hugging Face for MiniCPM-V 2.0 and MiniCPM-Llama3-V 2.5.
+We support simple fine-tuning with Hugging Face for MiniCPM-V 2.0 and MiniCPM-Llama3-V 2.5.
 
 [Reference Document](./finetune/readme.md)
 
 ### With the SWIFT Framework <!-- omit in toc -->
 
-We now support finetune MiniCPM-V series with the SWIFT framework. SWIFT supports training, inference, evaluation and deployment of nearly 200 LLMs and MLLMs . It supports the lightweight training solutions provided by PEFT and a complete Adapters Library including techniques such as NEFTune, LoRA+ and LLaMA-PRO.
+We now support MiniCPM-V series fine-tuning with the SWIFT framework. SWIFT supports training, inference, evaluation and deployment of nearly 200 LLMs and MLLMs . It supports the lightweight training solutions provided by PEFT and a complete Adapters Library including techniques such as NEFTune, LoRA+ and LLaMA-PRO.
 
 Best Practices：[MiniCPM-V 1.0](https://github.com/modelscope/swift/blob/main/docs/source/Multi-Modal/minicpm-v最佳实践.md), [MiniCPM-V 2.0](https://github.com/modelscope/swift/blob/main/docs/source/Multi-Modal/minicpm-v-2最佳实践.md)
 

docs/compare_with_phi-3_vision.md

@@ -0,0 +1,31 @@
+## Phi-3-vision-128K-Instruct vs MiniCPM-Llama3-V 2.5
+
+Comparison results of Phi-3-vision-128K-Instruct and MiniCPM-Llama3-V 2.5, regarding the model size, hardware requirements, and performances on multiple popular benchmarks.
+
+我们提供了从模型参数、硬件需求、全面性能指标等方面对比 Phi-3-vision-128K-Instruct 和 MiniCPM-Llama3-V 2.5 的结果。
+ 
+ ## Hardeware Requirements （硬件需求）
+
+With in4 quantization, MiniCPM-Llama3-V 2.5 delivers smooth inference of 6-8 tokens/s with only 8GB of GPU memory.
+
+通过 in4 量化，MiniCPM-Llama3-V 2.5 仅需 8GB 显存即可提供 6-8 tokens/s 的流畅推理。
+
+| Model（模型）                | GPU Memory（显存）        |
+|:----------------------|:-------------------:|
+| [MiniCPM-Llama3-V 2.5](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5/)  | 19 GB   |
+| Phi-3-vision-128K-Instruct | 12 GB |
+| [MiniCPM-Llama3-V 2.5 (int4)](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-int4/)  | 8 GB |
+
+## Model Size and Peformance （模型参数和性能）
+
+
+
+| | Phi-3-vision-128K-Instruct | MiniCPM-Llama3-V 2.5|
+|:-|:----------:|:-------------------:|
+| Size（参数） | **4B** | 8B|
+| OpenCompass | 53.7 | **58.8** |
+| OCRBench | 639.0  | **725.0**|
+| RealworldQA | 58.8 | **63.5**|
+| TextVQA | 72.2 | **76.6** |
+| ScienceQA| **90.8** | 89.0 | 
+| POPE | 83.4 | **87.2** |