Zhe Chen

Results 316 comments of Zhe Chen

最新的V1.5模型已经支持了batch inference,具体可以看这里的代码样例: https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5#model-usage 其中的# batch inference (single image per sample)这部分

请问现在这个问题解决了吗

感谢您的建议。我最近会转换一下量化模型并上传到hugging face。

> 咱们的(原来是v1-2plus已基本够用,版本3输出位置是按照1000*1000),很强。 还有咱们这应该没有专门针对测试数据,因为我实测身份证和营业执照等关键信息提取,都非常好,star应该上万,其他人没有发现此处是宝。 感谢反馈!目前已经训好了支持到2K-4K分辨率的模型,刷点性能和实际体验都有大幅提升,预计下周会放出来,可能这两天会更新一个预览的demo。

> @czczup 哇塞效果这么好。普通消费者只能下载 10G左右的模型; 有试试V1.5的demo吗

在InternVL-Chat-V1-2-Plus中我们用的格式是这样: ``` { "id": 0, "image": "images/5.png", "conversations": [ { "from": "human", "value": "\nPlease provide the bounding box coordinate of the region this sentence describes: XXX" }, { "from": "gpt",...

我们的v1.2-plus使用的中文数据中有一些构造的负样本,是这样的格式: ``` {"image": "train2017/000000179725.jpg", "conversations": [{"from": "human", "value": "\n这是哪个旅游景点?"}, {"from": "gpt", "value": "这张图片可能并非拍摄的旅游景点,而是其他场景。"}], "id": 6076} {"image": "train2017/000000000384.jpg", "conversations": [{"from": "human", "value": "\n图片中的人物是谁?"}, {"from": "gpt", "value": "图片中似乎没有人物,因此我无法做出回答。"}], "id": 399} {"image": "train2017/000000070125.jpg",...

> > 我们的v1.2-plus使用的中文数据中有一些构造的负样本,是这样的格式: > > ``` > > {"image": "train2017/000000179725.jpg", "conversations": [{"from": "human", "value": "\n这是哪个旅游景点?"}, {"from": "gpt", "value": "这张图片可能并非拍摄的旅游景点,而是其他场景。"}], "id": 6076} > > {"image": "train2017/000000000384.jpg", "conversations": [{"from": "human", "value": "\n图片中的人物是谁?"},...

Thank you for your interest. Currently, we do not offer such code to deploy the model as an API; our existing code only supports deploying the model as a local...

You can now use [lmdeploy](https://github.com/InternLM/lmdeploy) to deploy InternVL-Chat as an API, or you can use this existing [API](https://rapidapi.com/adushar1320/api/internvl-chat).