pp

CeMAT pre-trained models download

1

Thanks for your work Where can I directly download the pre-trained model and vocab you mentioned in **CeMAT** ReadMe?

Error when training on ScanNet dataset

6

I followed the Training on ScanNet in README. _Phase 1 (the first 0-20 epoch), training single fragments. MODEL.FUSION.FUSION_ON=False, MODEL.FUSION.FULL=False,_ the model cannot work and got the error. Traceback (most recent...

about post normalization

4

I have added post layer-normalization option to OpenNMT, but the translation BLEU score is much lower than pre layer-normalization (in OpenNMT, default is pre-norm, and my training model architecture is...

add post-normalization option

Where to find the cifar-100 train/test/solver configure file

4

Would you please upload the cifar-100 net configure file? Thanks!!!

### Reminder - [X] I have read the README and searched the existing issues. ### Reproduction [Code](https://github.com/hiyouga/LLaMA-Factory/blob/4728fe62d183603f08c3c1fa94f18a7c67d48b85/src/llamafactory/data/processors/supervised.py#L118C3-L127C70) 实际跑下来，发现打印的样本确实是被截断的，不是按照预期的能够保证一条样本能在一个model_inputs中 同时代码里面没有看到针对multipacking，attention mask相关的对应改动 ### Expected behavior build inputs with format ` X1 Y1...