LianghuiGuo issues

Results 12 issues of


                                            LianghuiGuo

[Question] RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

### Question I met this error when finetuning the model, and the environment configuration was based on the official environment. ```python Loading checkpoint shards: 100%|██████████| 33/33 [02:49

size mismatch for bert.embeddings.word_embeddings.weight

Hello, I have trained a Bert with vocab_size 21128, and I noticed that in BLIP the vocab_size should be 21130 (including 2 additional tokens:DEC,ENC). However, this difference caused a shape...

grdio加载模型卡住

app_deepseek.py 脚本，gradio加载模型（deepseek-vl-7b-chat），一直卡在loading，这是什么原因呢？ V100的卡

参考LLAVA的方式构建自己的数据集，数据量14w，按照官方给的方式进行finetune，发现进入trainer.train()之后就hang住了，strout和strerr也没有信息，没有报错，请问是哪里不对吗 strout中的输出 ```python [2023-12-04 15:00:43,681] [WARNING] [partition_parameters.py:823:_post_init_method] param `cls_token` in MplugOwlVisionEmbeddings not on GPU so was not broadcasted from rank 0 [2023-12-04 15:00:43,747] [WARNING] [partition_parameters.py:823:_post_init_method] param `position_embedding` in MplugOwlVisionEmbeddings not...

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

mplug-owl2，finetune遇到这个问题，环境配置按照官方来的，数据用的32个测试数据，仿照LLAVA的数据构建 ```python Loading checkpoint shards: 100%|██████████| 33/33 [02:49

请问是否支持中文数据微调呀？May I finetune mPLUG-Owl with chinese image-text pair?

可否用中文的图文对进行SFT呢？ May I finetune mPLUG-Owl with chinese image-text pair?

Thanks for the great work! I am wondering whether mPLUG-Owl2 have OCR ability?

Does mPLUG-OWL2 have OCR ability? 请问训练数据中有OCR数据么？

💡 [REQUEST] - <title>请问有方法可以提取图文embedding吗？

question

💡 [REQUEST] - <title> 请问可以支持pretrain吗？

question

请问支持中文数据微调/推理吗？

非常棒的工作！想了解下，请问支持中文数据微调/推理吗？