Ecosyste.ms: Timeline

Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.

OpenBMB/MiniCPM-V

AssassinGQ starred OpenBMB/MiniCPM-V
zxrys starred OpenBMB/MiniCPM-V
Affirc60sec starred OpenBMB/MiniCPM-V
fish-can starred OpenBMB/MiniCPM-V
choppertime starred OpenBMB/MiniCPM-V
yuanxiaoyu1 starred OpenBMB/MiniCPM-V
robcsaa starred OpenBMB/MiniCPM-V
belingud starred OpenBMB/MiniCPM-V
cnwarden starred OpenBMB/MiniCPM-V
zhifac starred OpenBMB/MiniCPM-V
mattiacurri starred OpenBMB/MiniCPM-V
kleinod123 starred OpenBMB/MiniCPM-V
Staszek-org starred OpenBMB/MiniCPM-V
Staszek-org starred OpenBMB/MiniCPM-V
zjmwqx created a comment on an issue on OpenBMB/MiniCPM-V
同问

View on GitHub

ostwilkens starred OpenBMB/MiniCPM-V
royzhang12 opened an issue on OpenBMB/MiniCPM-V
[BUG] <title> 请问在用deepspeed zero3 训练的过程应为minicpm navit的逻辑会导致不同rank上的feature size 不同这样会hang住,这个是怎么解决的?zero2是没有问题的
### 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 ...
aimvp-dev starred OpenBMB/MiniCPM-V
yangmengjiang6 starred OpenBMB/MiniCPM-V
CCRss created a comment on an issue on OpenBMB/MiniCPM-V
We will check if that will not work we will just try other approach data might be the key. Maybe you can provide me some directions of how to connect MiniCPM vision encoder with different model...

View on GitHub

LDLINGLINGLING created a comment on an issue on OpenBMB/MiniCPM-V
This may make sense, but it depends on how much data you have for coordinates. If the amount of data is not particularly large, I would recommend that you directly affect our model.

View on GitHub

CCRss created a comment on an issue on OpenBMB/MiniCPM-V
Thanks. We are planning to fine-tune on the task specific datasets for our language after we will be able to connect the vision encoder and 70B llm part. What do you think about training with 70B ...

View on GitHub

LDLINGLINGLING created a comment on an issue on OpenBMB/MiniCPM-V
I think this is possible, but the first point is that the code needs to be changed. Second point, you may need to use a lot of data to retrain the alignment of images and text.

View on GitHub

SrikanthChellappa created a comment on an issue on OpenBMB/MiniCPM-V
Thanks @LDLINGLINGLING for the link. I saw this link before this post but couldn't understand the context as it was in Chinese and with translation I was losing the complete context. can you pls as...

View on GitHub

CCRss created a comment on an issue on OpenBMB/MiniCPM-V
@LDLINGLINGLING Thanks for response. So it's not possible to connect MiniCPM vision part with the 70B quantized model for example? Because previously I connected to llm part 8B fine-tuned versi...

View on GitHub

ychy00001 closed an issue on OpenBMB/MiniCPM-V
[BUG] 微信群加不了了,抓紧在更新一个吧
### 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 ...
LDLINGLINGLING created a comment on an issue on OpenBMB/MiniCPM-V
感谢反馈,已经更新了

View on GitHub

LDLINGLINGLING pushed 1 commit to main OpenBMB/MiniCPM-V

View on GitHub

Load more