Skip to content

Issues: yanqiangmiffy/InstructGLM

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

22 Open 11 Closed
22 Open 11 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

Problems in train_deepspeed.py with ZeRO stage 1|2|3
#34 opened Sep 7, 2023 by zjhJOJO
用tokenizer_dataset_rows.py转换自己的数据报错datasets.builder.datasetgeneraationerror
#33 opened May 9, 2023 by cat1222
使用lora训练，使用web_demo加载lora权重后，结果跟原生chatglm结果一样，lora权重没生效，这个是什么原因呢
#32 opened May 6, 2023 by AnddyWang
1
用BelleGroup/train_1M_CN训练后，为什么用数据集里的问题测，回答不一样
#31 opened May 5, 2023 by czhcc
调教后的逻辑能力如何？
#30 opened Apr 29, 2023 by daiaji
1
train_lora最低需要多大显存GPU可以训练？除了batch size 还有别的参数可以降低显存使用吗？
#29 opened Apr 27, 2023 by twosnowman
2
用peft加载lora后，generate时报错ValueError: 130000 is not in list，加载lora之前推理是正常的
#28 opened Apr 25, 2023 by BIGPPWONG
请问下train_deepspeed.py 怎么引入lora.pt
#27 opened Apr 20, 2023 by AlexXx-Wu
1
ValueError: ChatGLMForConditionalGeneration does not support gradient checkpointing.
#25 opened Apr 19, 2023 by deepeye
7
datasets.builder.InvalidConfigName: Bad characters from black list '<>:/\|?*' found in 'data/belle_data.json'. They could create issues when creating a directory for this config on Windows filesystem.
#23 opened Apr 19, 2023 by deepeye
1
4张32G的可以吗，作者可以用你写的其他开源数据集finetune看看效果吗，再放出转换和训练代码
#21 opened Apr 15, 2023 by hangzeli08
2
4张 12G的 3060能训练吗
#20 opened Apr 14, 2023 by zlszhonglongshen
2
运行web_demo_alpaca_lora.py报错，是单纯的显存不够嘛
#19 opened Apr 14, 2023 by tianmala
1
训练python train_lora.py的时候显示 ModuleNotFoundError: No module named 'configuration_chatglm'
#18 opened Apr 13, 2023 by dragononly
3
测试数据打不开https://huggingface.co/datasets/BelleGroup/generated_train_0.5M_CN
#17 opened Apr 12, 2023 by dragononly
2
微调2:BELLE中文指令数据的问题
#16 opened Apr 12, 2023 by czhcc
1
运行 finetune.py 遇到问题：OSError: /data/pretrained-chatglm-6b/ does not appear to have a file named config.json
#13 opened Apr 4, 2023 by xubuvd
1
最新update的代码中，web_demo推理时报错
#12 opened Apr 3, 2023 by feyxong
2
关于训练完成后，生成的答案总是带一些莫名奇妙的Q，A数据，真的不造是哪里出了问题，还望大佬赐教！谢谢！
#11 opened Apr 2, 2023 by UMU689
1
关于多轮对话的疑问
#9 opened Mar 29, 2023 by ZeyuTeng96
web_demo_belle生成结果时有大段重复的问题
#8 opened Mar 29, 2023 by JiayiFu
10
ValueError: 150000 is not in list
#5 opened Mar 25, 2023 by superhg
5
ProTip! Add no:assignee to see everything that’s not assigned.