liucongg ChatGLM-Finetuning issues

liucongg / ChatGLM-Finetuning

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等

2.62k stars 291 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

配置环境出错

#147 nothing7744 opened 1 day ago
0
TypeError

#146 ZCzzzzzz opened 3 weeks ago
1
P-tuning

#145 JulyCaoJie opened 2 months ago
0
支持glm4

#144 tcxia opened 2 months ago
0
python3.8、3.9、3.10安装torch都报错

#143 ZzYAmbition closed 2 months ago
1
RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.

#142 cqray1990 opened 3 months ago
1
关于流水线并行的一个问题

#141 Cheung-Z opened 3 months ago
0
RuntimeError: The server socket has failed to listen on any local network address. The server socket has failed to bind to [::]:520 (errno: 13 - Permission denied). The server socket has failed to bind to ?UNKNOWN? (errno: 13 - Permission denied).

#140 ysz2000 opened 5 months ago
0
请问如何制作数据集

#139 Franklin-L opened 5 months ago
0
只有训练没有验证

#138 NanZhang1991 opened 6 months ago
1
问题

#137 wuguangshuo opened 7 months ago
0
关于Pipeline Parallel的data_iter的问题

#136 Coobiw closed 7 months ago
1
local_rank默认设置-1，在执行torch.distributed.get_rank()时报错：RuntimeError: Default process group has not been initialized, please make sure to call init_process_grroup.

#135 dczhangii opened 7 months ago
1
ChatGLM3四卡训练出错了

#134 eanfs opened 7 months ago
1
有关混合精度训练的问题

#133 zzhdbw opened 7 months ago
0
ptuning是损失为nan

#132 silence-moon opened 7 months ago
0
chatglm3 单卡训练报错了

#131 eanfs opened 7 months ago
4
在RTX 4090 上微调chatglm3报这个错：Current loss scale already at minimum - cannot decrease scale anymore

#130 450586509 opened 7 months ago
1
使用README中的代码,报错TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

#129 sunheyang1 opened 7 months ago
0
没有验证过程?

#128 xiaozhubenben opened 8 months ago
0
ChatGLM3训练时报错TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

#127 AILWQ opened 8 months ago
16
--model_name_or_path', '../THUDM/chatglm-6b'参数什么错误

#126 daiyucan opened 8 months ago
1
RuntimeError: Error building extension 'fused_adam'

#125 LeFuGang opened 8 months ago
2
python版本

#124 liujinchang closed 8 months ago
1
peft==0.5.0怎么安装

#123 zhl970124 closed 8 months ago
1
运行trainer时报错Error building extension 'fused_adam'

#122 J-G-Y opened 8 months ago
4
File "/root/anaconda3/envs/llm/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 847, in __init__ setattr(self, key, value) AttributeError: can't set attribute 'eos_token'

#121 zzdxjtu opened 8 months ago
2
ChatGLM3-6B-32k 请问chatglm3里面的代码除了模型名字以外别的需要修改吗

#120 diorw opened 8 months ago
1
解决 AttributeError: 'ChatGLMTokenizer' object has no attribute 'tokenizer'

#119 gangtie95 closed 8 months ago
1
计划再支持下chatglm3不？

#118 zjcanjux closed 8 months ago
2
两张2080ti多卡加载微调

#117 Lxhnnn opened 9 months ago
1
OSError: ChatGLM2-6B is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'

#116 xxtyy opened 10 months ago
4
请问是否考虑支持其他开源llm呀？

#115 Irvingao closed 8 months ago
1
mask_token = 150001

#114 Geministudents closed 10 months ago
1
运行chatglm2单卡微调的时候遇到了ModuleNotFoundError: No module named 'peft'问题

#113 Alan-JW closed 10 months ago
3
tokenizer.bos_token_id 为啥不正确呢？

#112 sjyttkl closed 8 months ago
2
预测代码

#111 HongTu0319 closed 8 months ago
4
多轮对话代码

#110 J-G-Y opened 10 months ago
1
predict error

#109 tcxia opened 10 months ago
0
梯度叠加

#108 Cheung-Z closed 8 months ago
2
4090显卡有办法跑这个项目吗？

#107 2279072142 opened 11 months ago
3
求问，train_pipeline.py是否可以直接用在chatglm2上！

#106 Chtholly1 closed 8 months ago
1
预测代码

#105 qaqrt opened 11 months ago
2
关于chatglm2与chatglm数据格式的问题

#104 Kayce001 opened 11 months ago
2
多机多卡运行 stage2 和stage3，stage3的训练时间是stage2的25倍，这结果合理吗

#103 yangzhipeng1108 opened 11 months ago
1
执行 train.py过程报错 exits with return code = -9

#102 yhx0105 opened 12 months ago
3
关于 RuntimeError: element 0 or 1 of tensors does not require grad and does not have a grad_fn的问题讨论

#101 karots123 opened 12 months ago
0
单卡正常，多卡报错

#100 SCU-JJkinging opened 12 months ago
5
增加chatGLM2+PT的预测代码

#99 micrazy opened 1 year ago
9
请问是否支持断点续训？lora和全参微调

#98 lianglinyi opened 1 year ago
1