Skip to content

Issues: OpenBMB/MiniCPM-V

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

100 Open 512 Closed
100 Open 512 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[BUG] <title> When using MiniCPM as the language Model, getting "data fetch error", bug in dataset.py file.
#702 opened Dec 24, 2024 by Aritra02091998
2 tasks done
README vllm section improved.
#701 opened Dec 22, 2024 by singing-cat
❓ [QUESTION] - Help Needed: Modify Refusal Removal Scripts to Work with MiniCPM-V-2_6 question Further information is requested
#700 opened Dec 20, 2024 by NullEqualsZero
[BUG] <title>TypeError: CPMTrainer.training_step() takes 3 positional arguments but 4 were given
#698 opened Dec 19, 2024 by FrancisFan98
2 tasks done
3
[llama] <.so版本不一致>
#697 opened Dec 18, 2024 by Heiheicxx
2 tasks done
💡 [REQUEST] - <title>MiniCPM-V 2.6 is supported in PaddleMIX by Paddle Team! question Further information is requested
#695 opened Dec 18, 2024 by luyao-cv
1
关于VisionEncoder里面的VIT: SigLIP SoViT-400m/14
#692 opened Dec 11, 2024 by henrycCoder
[ollama] - 请问这个数据有误吗？ question Further information is requested
#691 opened Dec 10, 2024 by auroralzone
[BUG] Visual embedding vector size
#690 opened Dec 9, 2024 by rokopi-byte
2 tasks done
1
[BUG] <title>
#689 opened Dec 9, 2024 by 66RomanReigns
2 tasks done
1
模型训练后推理出现乱码 question Further information is requested
#688 opened Dec 9, 2024 by MickeyFei
1
💡 [REQUEST] - <title>讀取並理解文件PDF question Further information is requested
#687 opened Dec 6, 2024 by aybs2060
2
minicpm-V2.6提取图片中的文本信息怎么输出置信度呢 question Further information is requested
#686 opened Dec 5, 2024 by zxy1029
[BUG] <title>MiniCPM-V 2.6跑demo，本身机器显存8G，使用cuda提示显存不够
#685 opened Dec 3, 2024 by nw-wf
2 tasks done
1
求教：为什么Resampler后，还可以做OCR识别，感觉已经在压缩的过程中，丢失了信息，做OCR识别任务会降低精度
#684 opened Nov 30, 2024 by alphanlp
1
[BUG] <title>Is there any restriction on images or datasets for fine-tuning vision encoder or llm of MiniCPM-v2.6?
#683 opened Nov 28, 2024 by Wytheyayaya
2 tasks done
1
💡 [REQUEST] - <title>給模型一個全新的名字跟形象 question Further information is requested
#682 opened Nov 28, 2024 by aybs2060
2
💡 [REQUEST] - <few shot learning（in-context learning）评估脚本或评估设置> question Further information is requested
#681 opened Nov 26, 2024 by ColorDavid
[BUG] <title>多图单轮对话全量SFT，loss 变为零
#679 opened Nov 25, 2024 by Evan9978
2 tasks done
5
你好，由于 minicpm2.6 的 pretrain ckpt 没有开源，所以这部分评测代码也没有提供，我们的 few-shot 推理方式可以参考 readme 部分的 icl 推理方式。
#676 opened Nov 20, 2024 by ColorDavid
1
[vllm] - <title> vllm 部署了API接口，示例里边有单张图片的推理，但是多张图片的推理，有参考示例吗？ question Further information is requested
#674 opened Nov 19, 2024 by lh3707
1
💡 [REQUEST] - <title>预训练相关 question Further information is requested
#672 opened Nov 18, 2024 by zhangzhixun1999
1
Can you provide pre-training files for MiniiCPM-V-2.0 version?
#671 opened Nov 17, 2024 by Leke-G
2 tasks done
微调中断后如何继续训练
#670 opened Nov 16, 2024 by wanghaolan123
1
💡 [REQUEST] - 希望能够实现函数调用的功能，并且提供说明文档，方便第三方写插件 question Further information is requested
#669 opened Nov 15, 2024 by Johnson-yue
3
ProTip! Find all open issues with in progress development work with linked:pr.