Issues
- 0
function attach() could not work
#76 opened by koishichann - 0
在训练deltamodel时如何定义优化器
#75 opened by liiizer - 1
- 3
- 0
A significant difference between the results obtained from testing after training and reloading the model after saving. How to save and reload the model correctly for reasoning?
#73 opened by FanY1999 - 0
- 0
- 0
DeltaCenter库找不到,是怎么回事?
#69 opened by tommickey2020 - 4
pip install opendelta报错
#56 opened by sslayer - 0
Opendelta是否计划加入llama系列模型?
#67 opened by Hanpx20 - 0
opendalta支持delta model. 的 p-tuning v2 嘛?
#66 opened by liweiqing1997 - 0
- 0
- 2
Examples related to the paper "Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models"
#63 opened by NtaylorOX - 1
为什么没有中文的README
#53 opened by EnHuiPug - 0
Fix for a Bug in BitFit for T5
#60 opened by prateeky2806 - 0
- 0
Where to find the trained delta checkpoints?
#58 opened by prateeky2806 - 1
save issue
#30 opened by zhujiajunbryan - 2
json.decoder.JSONDecodeError when calling DeltaCente.OssClient.download function
#36 opened by Hemuhui - 3
does opendelta support gradient_checkpointing?
#39 opened by hmzo - 1
- 1
tutorial doc bug
#42 opened by zhujiajunbryan - 3
Example of multi-task
#43 opened by NtaylorOX - 1
`ModuleNotFoundError` caused by `turtle` package
#47 opened by jon-tow - 1
导入报错
#49 opened by Mryangkaitong - 3
Flash Attention and Open Delta LoRA
#50 opened by conceptofmind - 1
- 1
通过setup.py安装提示error: aiohttp 4.0.0a0 is installed but aiohttp!=4.0.0a0,!=4.0.0a1 is required by {'fsspec'}
#45 opened by daliang0222 - 0
tutorial$ python 0_basic.py 存在错误
#52 opened by xk503775229 - 0
fix
#51 opened by xk503775229 - 0
- 2
XGLM: How to apply OpenDelta to a new model?
#12 opened by un-certainty - 1
- 0
- 2
Is it possible to extract the Visualization module as an independent python packages?
#40 opened by Dounm - 1
初始化基类时,如果填了unfrozen_modules,没有unfrozen_modules赋值
#38 opened by dabaoka - 1
- 1
compatibility with pytorch
#26 opened by CaffreyR - 1
LowRankAdapter not working with Bert models
#23 opened by MrigankRaman - 1
RuntimeError: This is a delta model, which should be attached to a backbone model and can't forward any data by itself. Please using the backbone model's forward function after attach the delta model to the backbone. eceived was empty, your model won't be able to train on it. Double-check that your training dataset contains keys expected by the model: args,kwargs,label_ids,label.
#25 opened by CaffreyR - 0
How to change the size of the dataset?
#27 opened by CaffreyR - 0
-
#24 opened by opalthailand - 1
Potential cuda device bugs
#21 opened by ShengdingHu - 1
- 2
- 1
error when running on multiple cards
#18 opened by wangdeze18 - 1
some bug about reparameterize flag in PrefixModel
#14 opened by yuto3o - 1
BitFit for GPT-2 Models
#17 opened by siddk - 2