Comments (2)
Hi @liberty-1776, thanks for raising the issue. Your suggestion is valuable, and we've updated the code. Meanwhile, even though the square brackets are included, the effect is just having a '[' after the start token '' and a ']' before the end token '', so we believe that the performance of the pretrained model will be almost the same after removing the square brackets. And the downstream performance should be the same as the results we report in paper (if not better) since the tokens from the downstream sequences do not have such issue.
from transpolymer.
Yeah, that's right
from transpolymer.
Related Issues (13)
- Finetuning attention maps HOT 5
- Issues with the running of Downsteam.py HOT 1
- Question about Tokenizer HOT 2
- OSError: Can't load tokenizer for 'roberta-base'. HOT 1
- RuntimeError: Error(s) in loading state_dict for DownstreamRegression: HOT 1
- Finetuned model HOT 3
- Different block_size for pretrain and finetune HOT 3
- Cloning Issue HOT 1
- Regarding Validation Error and Testing Error HOT 1
- Regarding Egc Dataset HOT 2
- Supplementary Vocab File HOT 4
- TypeError when using Downstream.py HOT 4
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 transpolymer.