alexiglad / EBT
PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning
Why this job: works in the areas we cover, but does not say which job it does
What it does
Energy-Based Transformers (EBTs) are a new approach enabling generalizable reasoning/System 2 Thinking on any problem/modality. We demonstrate the scalability of EBTs by becoming the first approach to outscale feed-forward Transformers across modalities and with respect to several axes including data, depth, parameters, FLOPs, etc. EBTs can think over every single prediction being made (i.e. every token in language modeling) and tend to generalize better than existing models.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Inactive
- Last commit 6 months ago
- Stars
- 665
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 92% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 93% closed
- 1 still open
- Pull requests
- 2 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| plastic-labs / tutor-gpt | 932 | 12 months ago | GPL-3.0 | No downloads |
| meta-prompting / meta-prompting | 331 | 3 months ago | MIT | No downloads |
| GAIR-NLP / MegaScience | 132 | 4 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 92%
- Shell 8%
Topics
- ai
- deep-learning
- generative-ai
- reasoning
- thinking
Project record
- JobOther AI tools
- StatusListed
- Commits21
- Forks91
- Watching12
- Stars in 28 days+4
- CreatedJun 26, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026