Upload folder using huggingface_hub

README.md

@@ -9,15 +9,15 @@ pipeline_tag: image-text-to-text
 
 [\[🗨️ Chat Demo\]](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)  \[🌟 [魔搭社区](https://modelscope.cn/organization/OpenGVLab) | [教程](https://mp.weixin.qq.com/s/OUaVLkxlk1zhFb1cvMCFjg) \]
 
-We are excited to introduce InternVL-Chat-V1-2. Inspired by [LLaVA-NeXT-34B](https://llava-vl.github.io/blog/2024-01-30-llava-next/), we have also adopted [Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B) as the language model. Below is the pipeline.
+We are excited to introduce [🤗 InternVL-Chat-V1-2](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-2). Inspired by [LLaVA-NeXT-34B](https://llava-vl.github.io/blog/2024-01-30-llava-next/), we have also adopted [Nous-Hermes-2-Yi-34B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B) as the language model. Below is the pipeline.
 
 <p align="center">
-  <img width="600" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/GIEKCvNc1Y5iMQqLv645p.png">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/GIEKCvNc1Y5iMQqLv645p.png" style="width: 70%;">
 </p>
 
-From the experimental results, **we've observed that a stronger language model (34B) can better leverage the powerful capabilities of our vision foundation model ([InternViT-6B](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2)).**
+From the experimental results, we've observed that **a stronger language model (34B) can better leverage the powerful capabilities of our vision foundation model.**
 
-For better training reproducibility, we follow the minimalist design and data efficiency similar to LLaVA-NeXT. To reduce training costs, we provide a pre-trained MLP projector and only employ around 1 million visual instruction tuning samples for SFT. Our model has a total of 40 billion parameters and can be trained within 1.5 days using 32 A100 GPUs. The code, data, and model will be made publicly available.
+For better training reproducibility, we follow the minimalist design and data efficiency similar to LLaVA-NeXT. To reduce training costs, we provide a [pre-trained MLP projector](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2/blob/main/mlp_projector/hermes_2_yi_34b.pth) and only employ around 1.2 million visual instruction tuning samples for SFT. Our model has a total of 40 billion parameters and can be trained within 1.5 days using 32 A100 GPUs. The code, data, and model have been made publicly available.
 
 ## Model Details
 
@@ -54,6 +54,7 @@ For better training reproducibility, we follow the minimalist design and data ef
 | LLaVA−NEXT−34B     | 672x672    | 51.1          | 44.7           | 46.5                    | 79.3          | 79.0             | -    | 1631/397 | 81.8                 | 87.7 | 69.5             | 75.9              | 63.8             | 67.1          |
 | InternVL−Chat−V1-2 | 448x448    | 51.6          | 46.2           | 47.7                    | 82.2          | 81.2             | 56.7 | 1687/489 | 83.3                 | 88.0 | 72.5             | 75.6              | 60.0             | 64.0          |
 
+- Note that we use the [official evaluation server](https://huggingface.co/spaces/whyu/MM-Vet_Evaluator) to test the MMVet scores, with `GPT-4-0613` serving as the judge model. Using different versions of GPT-4 as the judge can result in significant score variations.
 - In most benchmarks, InternVL-Chat-V1-2 achieves better performance than LLaVA-NeXT-34B.
 
 Here, we have conducted only a simple performance comparison. For more detailed performance information and additional evaluation metrics, please refer to our performance summary table.