hello,I have trained this model for OCR and grounding tasks, maybe it will help you, the tutorial is below:https://modelbest.feishu.cn/wiki/HLRiwNgKEic6cckGyGucFvxQnJw?from=from_copylink
Hello, this method is not possible because we have aligned the language model and the image model. If you do this, even if you can run through the code, the effect will be very poor. In addition, l...
### 是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答? | Is there an existing ...
The interface to minicpm v2.6 is data, **inputs can't reasonably get data, when the model.eval mode is turned on, there will be a problem of not finding the input data, after experimenting to pass ...