GitHub / Spico197 / MoE-SFT

🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts

JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Spico197%2FMoE-SFT
PURL: pkg:github/Spico197/MoE-SFT

Stars: 39
Forks: 0
Open issues: 1

License: apache-2.0
Language: Python
Size: 552 KB
Dependencies parsed at: Pending

Created at: about 1 year ago
Updated at: about 2 months ago
Pushed at: 10 months ago
Last synced at: about 2 months ago

Topics: dynamic-sampling, instruction-tuning, large-language-models, mixture-of-experts

Loading...