HectorHHZ/ExpertCondenser
Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning (COLM 2026): ExpertCondenser: SFT for sparse MoE LLMs with gated condenser experts. Official code.
ORIGINAL REPOSITORY
HectorHHZ/ExpertCondenser ↗GitHub activity
- Stars
- 5
- Forks
- 1
- Open issues and PRs
- 1
- Repository size
- ~156 KB
- Default branch
- main
- Created
- Jan 7, 2026
- Repository updated
- Sep 30, 2026
- Last push
- Sep 21, 2026
- Language
- Python
- License
- Apache-2.0
Topics colm2026 · deepseek · expert-routing · large-language-models · llm · load-balancing · mixture-of-experts · moe · moe-finetuning · olmoe · peft · qwen
Repository-wide figures from GitHub, checked Nov 6, 2026. Stars are endorsements, not a Mega AI Hub quality rating. Repository size is GitHub’s estimate; a ZIP download may differ.
Resource information
- Original repository
- HectorHHZ/ExpertCondenser
- Credit basis
- GitHub repository owner or organization; individual authorship is not asserted
- Publisher
- HectorHHZ
- Upstream last modified
- Sep 30, 2026
- Official website
- https://github.com/HectorHHZ/ExpertCondenser
- Languages
- Python
- Access
- Open original GitHub repository; publisher terms apply
- Last checked
- Nov 6, 2026
- License
- Apache-2.0
- Last record update
- Nov 6, 2026