LM-Dispersion
[๐๐๐ ๐ ๐ฎ๐ฌ๐ฎ๐ฒ] Dispersion loss counteracts embedding condensation and improves generalization in small language models
ChenLiu-1996/LM-Dispersion
View on GitHub โ[๐๐๐ ๐ ๐ฎ๐ฌ๐ฎ๐ฒ] Dispersion loss counteracts embedding condensation and improves generalization in small language models
LM-Dispersion grew +0.0% in the last 30 days, ranks 85th of 103 in Pretraining & Training, last commit 125 days ago.
Star trajectory
115 days tracked2026-07-02123 stars today2026-10-25
Momentum
+0.0% in 30d, below the Pretraining & Training median of +0.0%.
Maintenance
Last commit 125 days ago, fresher than the median of 163d.
How it compares in Pretraining & Training
LM-Dispersion
123
stars
+0.0% 30d
commit 125 days ago
Pretraining & Training median
316
stars
+0.0% 30d
commit ~163d ago
Leader ยท maxtext
2.4k
stars
+0.9% 30d
commit today
Ranked 85th of 103 by stars.
JustVugg/nanoeuler126-3ShimShim46/HFT-CNN124-1
ChenLiu-1996/LM-Dispersion123
DeepExperience/Harness-R1122+1Shanghua-Gao/RSI-Jev122+1- Language
- Python
- License
- Other
- Contributors
- 5
- Forks
- 6
- Watchers
- 1
- Open issues
- 0
- Releases
- 0
- Created
- 2025-04-16
- Stars this week
- +0
You've seen where LM-Dispersion stands today.
Get the moves before everyone else: the 5 Pretraining & Training repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.