Comments (3)
StillKeepTry
commented on September 1, 2024
This file maybe ok
from mpnet.
commented on September 1, 2024
Hate to reopen this issue, but using the above file, I'm getting an error on line 67 that 'decoder.sentence_encoder.relative_attention_bias.weight' doesn't exist in the original state dict. If I comment out this line, everything else is fine. Any idea if the name in the state dict has changed? Is it okay to ignore this when converting the model?
from mpnet.
commented on September 1, 2024
Never mind here, I realized I was using mpnet_base and not mpnet_rel_base
from mpnet.
Related Issues (20)
- could you release the finetune performance with fewer epoch on glue? HOT 1
- Setting 'max_len_single_sentence' is now deprecated. This value is automatically set up. HOT 1
- How to continue pretraining from the released checkpoint? HOT 3
- The exact English pretraining data and Chinese pretraining data that are exact same to the BERT paper's pretraining data. HOT 1
- does it support cuda HOT 1
- SQUAD2.0 test数据集结果
- The future is to combine MPNet with other language models innovations
- How to use deepspeed?
- rgument --arch/-a: invalid choice: 'mpnet_rel_base'这是为什么？
- Inconsistencies between data collator output and masked permute in original paper
- AssertionError: cannot specify cutoff larger than vocab size
- input mode questions? HOT 1
- Access to the released fairseq checkpoint HOT 4
- 关于SQuAD 2.0的评估 HOT 6
- MPNet如何训练长序列分类任务IMDB和RACE呢？ HOT 1
- Is there results on GLUE for MPNet which is pre-trained on 16G corpora?
- 可否圈下重点代码部分，fairseq代码太多 HOT 1
- 关于MPNet在GLUE dev集合上结果的疑问？ HOT 1
- Training on SQUAD2 gives less results on Evaluation set (Research Paper shows better results) HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mpnet.