Xing Long comments

Results 8 comments of


                                            Xing Long

About BP problem mentioned in the introduction

Thanks a lot for your prompt and insightful response! I have a bit of confusion and would appreciate your help in identifying where my understanding might be incorrect: The reason...

the standard deviation of the activation

Thanks a lot. So we just calculate the standard deviation of 100 values. Take the top 1 as an example: it might be the 2533rd dimension of the starting token...

NCCL broken pipe

Is there any solution now? Thanks! @Faustrazor @Eggwardhan

ChatAPI - ERROR - HTTPSConnectionPool(host='api.openai.com', port=443): Max retries exceeded with url: /v1/chat/completions (Caused by ProxyError('Unable to connect to proxy', NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f481233f640>: Failed to establish a new connection: [Errno 111] Connection refused')))

hello, I meet the same question, did you solve it?

About pretrain script and data of LLaVA-NeXT

data is available here https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Data, as for training code, you can use https://github.com/xiaoachen98/Open-LLaVA-NeXT, code is easy to use

torch_dtype of vision_config became float32 after full tuning

@Ego-J @hiyouga Have you solved this problem? I have met the same issue

如何使用api调用qwen2-vl-72b的模型来进行视频分析呢

![image](https://github.com/user-attachments/assets/58d4761f-5a77-425b-855b-448890a14bbb) 试了一下目前api形式的inference似乎并不支持video这种类型请问目前有解决这个吗 @AHPUymhd @SimonWXW @xieyongshuai 感谢！

TypeError: Couldn't cast array of type string to null in long json

@DronHazra @renweizhukov Is this fixed in the latest version?