Comments (6)
Hi,
Thanks for the question.
I think for this version, I didn't change the library part, so it shouldn't affect the Diffusion-LM code if you just use your original transformer install. (There is another version where I changed the generation_util.py to implement PoE decoding, but it's not here.)
I changed some code here: Diffusion-LM/transformers/examples/pytorch/language-modeling/*
to implement some baselines and classifier models.
from diffusion-lm.
Thanks so much @XiangLi1999 ! So is it safe to say that, for those of us who just want to reproduce your model we can just install the transformers
from pip or conda and be fine?
from diffusion-lm.
For everyone who wants to see the detailed differences. I searched for the commit with the minimum amount of differences to the forked code in the project.
Apparently this was forked from commit 8ce133063120683018b214fe10d1449e4c2401da of https://github.com/huggingface/transformers
from diffusion-lm.
yeah, I have the same question!
from diffusion-lm.
Hi @XiangLi1999
this is a bad idea to fork the codes of another library, and make your codes super untidy, this is not clear which files have been changed and hard to follow the method implementation. please do NOT fork a library, and modify the files and install the original library.
from diffusion-lm.
Hi @XiangLi1999
thanks for sharing the codes. About "There is another version where I changed the generation_util.py to implement PoE decoding, but it's not here." so you mean there is some parts of the codes which does not exist in the repo? I greatly appreciate if you could share all parts of the codes to be able to reproduce the results.
Many thanks
from diffusion-lm.
Related Issues (20)
- I wander where to find the model in the predictability HOT 1
- Training on A100
- Separate weights for word embedding and lm-head?
- Questions about the result of success rate of PPLM? HOT 2
- Why not directly use Emb(W) as X_0? HOT 2
- Error when running training script on Google Colab HOT 2
- Fail to load GPT2 pretrained model for attribute controled generation
- Reproducing Table 5: Sentence Infilling - CIDEr / BLEU-4 metrics HOT 1
- Baseline reproduction
- error when runing:Exception in thread Thread-4:·······ValueError: signal number 32 out of range
- Which classifier to use in custom_trainer.py for controllable generation?
- About the tT_loss HOT 1
- The difference between this code and the paper "IDDPM" in the run_loop function in train_util.py.
- The relevant code that caused the error is in the Controllable Text Generation section, after the model trained for 6 epochs and started evaluating, it raised a KeyError: 'eval_loss' HOT 2
- Questions about the NLL loss
- E2E training procedure
- Issue while generating controllable text generation
- How to Execute the Semantic Content Subtask with infill.py
- Seq2Seq tasks with Diffusion LM
- Difficulty in running code
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 diffusion-lm.