Comments (1)
Hi, we randomly initialized the embeddings and trained them end-to-end, so it is the same setting with Diffusion-LM. We also tried the second setting, which is compared with joint E2E training in our paper (Table 3). The line you quote loads the 128d random embeddings but they are not used in the later training, and we keep this interface in case you need to initialize them in other settings. For DiffuSeq, the actually used word embedding is:
DiffuSeq/diffuseq/transformer_model.py
Line 55 in 8bfafcb
from diffuseq.
Related Issues (14)
- Great work! looking forward to the code release. HOT 1
- rounding issue HOT 1
- Questions about TransformerNetModel initialization HOT 2
- use additional model to guide text generation HOT 1
- Why no attention mask used? HOT 1
- What is the `tT_loss`? HOT 2
- When will the code be open source? HOT 1
- Problems about running code. HOT 2
- Problems of running time and microbatch ? HOT 10
- Pretrain DiffuSeq? HOT 1
- Problem about Commonsense Conversation Dataset HOT 1
- Problem of Decoding HOT 2
- Pretrained checkpoint for QG
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 diffuseq.