Skip to content

Issues: XiangLi1999/Diffusion-LM

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

51 Open 20 Closed
51 Open 20 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Is there any clear protocol for re-implementing this paper?
#73 opened Aug 22, 2024 by Dandelionym
Difficulty in running code
#72 opened Jun 10, 2024 by ajtheb
Seq2Seq tasks with Diffusion LM
#71 opened Feb 20, 2024 by chiral-carbon
How to Execute the Semantic Content Subtask with infill.py
#70 opened Jan 2, 2024 by pluto12x
Issue while generating controllable text generation
#69 opened Nov 28, 2023 by heychhavi
E2E training procedure
#67 opened Aug 17, 2023 by elephantmipt
Questions about the NLL loss
#66 opened Jun 20, 2023 by AlonzoLeeeooo
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'
#65 opened Apr 19, 2023 by Markkk111
2
The difference between this code and the paper "IDDPM" in the run_loop function in train_util.py.
#64 opened Apr 18, 2023 by xyz321123
About the tT_loss
#63 opened Apr 16, 2023 by zzc681
2
Which classifier to use in custom_trainer.py for controllable generation?
#62 opened Apr 13, 2023 by CSerxy
Baseline reproduction
#60 opened Mar 29, 2023 by YANI-ALT
Reproducing Table 5: Sentence Infilling - CIDEr / BLEU-4 metrics
#59 opened Mar 29, 2023 by yair-schiff
1
Fail to load GPT2 pretrained model for attribute controled generation
#58 opened Jan 26, 2023 by Rongzhi-Dong
Why not directly use Emb(W) as X_0?
#56 opened Jan 12, 2023 by leekum2018
2
Separate weights for word embedding and lm-head?
#54 opened Dec 28, 2022 by zeyun-zhong
Training on A100
#53 opened Dec 13, 2022 by mathematiguy
I wander where to find the model in the predictability
#52 opened Dec 11, 2022 by Layort
1
some problems on reproducing the results
#51 opened Nov 27, 2022 by arealgoodname
Training Cost due to the EMA mechanism
#50 opened Nov 25, 2022 by Lancelot39
Do we need to scale word embeddings to [-1, 1]?
#49 opened Nov 19, 2022 by tj-zhu
3
Why only padding tokens are generated after a period of training, but no words?
#48 opened Nov 17, 2022 by greens007
How could I perform semantic experiment in e2e dataset?
#46 opened Nov 9, 2022 by WangCan1178
2
Is the embedding model trainable during the training process?
#42 opened Oct 31, 2022 by smiles724
3
How to deal with sequences with different lengths?
#41 opened Oct 27, 2022 by sunhaozhepy
1
ProTip! What’s not been updated in a month: updated:<2024-10-11.