Comments (4)
For character-level model, how to set the termination mark, the sequence generated behind are meaningless spaces, but afraid that some sentences have spaces.
like "" will be sepreate "<" "E" "O" "F" ">"
from megabyte-pytorch.
@relic-yuexi small question since looks like you were able to make the code work. Can you show me in some way how to make this work ? Sorry I'm new to AI stuff
from megabyte-pytorch.
Me too. I just want to makea small GPT-like model in chinese. By my experiment, it looks like it has a faster speed than the tradtional Transfomer. And it can use none complex tokenizer, i just use the func ord() to tokenizer the unicode.
Just input some text as the dataset, then modify the train.py as you like.
from megabyte-pytorch.
When i used the ord(" ") as a pad_id, it will lead to nan loss and hard training and error code.
from megabyte-pytorch.
Related Issues (13)
- Minor shape error HOT 1
- the patch embbeder implementations are different from the original paper HOT 4
- Training Results and Scaling HOT 1
- Why your Attention impl use kv dimention dim_head instead of inner_dim? HOT 1
- Evaluation metric bits-per-byte
- GPU used for original paper experiments HOT 1
- Why does it expect tokens? HOT 1
- What are the implications of this model? HOT 4
- the string is still divided into pieces HOT 1
- translation of model sizes from paper to model definition
- No available kernel error HOT 1
- some implementations are different from the original paper HOT 2
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 megabyte-pytorch.