Skip to content

Issues: OpenBMB/MiniCPM

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

33 Open 178 Closed
33 Open 178 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

[Feature Request]: post pre-training feature New features
#260 opened Nov 13, 2024 by zhangzhixun1999
请问是否可以提供转成onnx的相关指导文档，谢谢
#259 opened Nov 7, 2024 by IeohMingChan
[Feature Request]: 建议将finetune里的.sh文件中的--include localhost:1更改为--include localhost:0 feature New features
#255 opened Oct 16, 2024 by wsstudent
1
[Feature Request]: 如果使用CPU的话，要求的CPU核数和内存大概是多大，运行4B的模型。 feature New features
#254 opened Oct 14, 2024 by zaojiahua
1
[Bad Case]: error loading model architecture: unknown model architecture: 'minicpm3' time=2024-10-12T20:12:01.292+08:00 level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: this model is not supported by your version of Ollama. You may need to upgrade" badcase Bad cases
#253 opened Oct 14, 2024 by Hoyxxx
3
[Bug]: MiniCPM3在做gptq量化时报错 bug Something isn't working triage
#252 opened Oct 11, 2024 by vokkko
1 task done
2
Due to Flashattention, inference cannot be performed on v100 badcase Bad cases
#249 opened Sep 28, 2024 by jiangchengchengark
1
[Feature Request]: MiniCPM3中是否还使用了“粗质量Stable+高质量Decay”？ feature New features
#248 opened Sep 28, 2024 by huyiwen
[Question]：请问llama.cpp部署中convert_hf_to_gguf时，为什么需要modify_tensors转换部分权重呢？
#247 opened Sep 25, 2024 by FdyCN
1
[Feature Request]: MiniCPM3-4B会考虑开源base权重么？ feature New features
#246 opened Sep 24, 2024 by Rookie-Kai
[Bug]: RuntimeError bug Something isn't working triage
#245 opened Sep 24, 2024 by WoNiuHu
1 task done
1
[Feature Request]: Need LoRA model in .gguf format feature New features
#243 opened Sep 20, 2024 by bioinformatist
2
V1.0测试数据和脚本的链接失效 badcase Bad cases
#240 opened Sep 17, 2024 by MAxx8371
[Feature Request]: 工具调用可以支持openai 的api function call吗 feature New features
#239 opened Sep 16, 2024 by lonngxiang
8
ImportError: cannot import name 'SamplerOutput' from 'vllm.sequence' (/root/miniconda3/lib/python3.11/site-packages/vllm/sequence.py bug Something isn't working triage
#236 opened Sep 14, 2024 by badarrrr
1 task done
1
[Bad Case]: 在机器上部署reranker模型之后，请求的时候报错了 badcase Bad cases
#230 opened Sep 13, 2024 by TOMATODA
@Kaguya-19
4
MiniCPM3微调
#229 opened Sep 13, 2024 by lifelsl
3
结构设计
#223 opened Sep 11, 2024 by slZheng077
持续预训练阶段的数据配比
#220 opened Sep 11, 2024 by zyzyyy123
[Feature Request]: 模型微调 feature New features
#213 opened Sep 9, 2024 by aph-asic
[Feature Request]: 哭着求MiniCPM 4和Ollama的集成？ feature New features
#204 opened Sep 6, 2024 by fishfree
18
[Bad Case]: function calling可以不用vllm吗？ badcase Bad cases
#203 opened Sep 6, 2024 by cristianohello
4
[Feature Request]: 笔记本NPU如何调用MiniCPM feature New features
#200 opened Sep 6, 2024 by R0k1e
1
[Feature Request]: 可否提供正確的CUDA version, PyTorch version, 以及 deepspeed version? feature New features
#194 opened Sep 1, 2024 by joyyang1215
1
请教一下你们预训练用了1.1T tokens，花了多少GPU和时间 badcase Bad cases
#190 opened Aug 20, 2024 by zyh3826
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.