ms-swift
JSON →A scalable lightweight infrastructure for fine-tuning large language models (LLMs), vision-language models (VLMs), and embedding models. Supports LoRA, QLoRA, full fine-tuning, and reinforcement learning methods like DPO, GRPO, and PPO. Version 4.1.3 is the latest, with releases every few weeks.
Traffic · last 30 days ↓75% vs prev 7d
total hits 15
actors 7 distinct systems
last hit 5d ago AhrefsBot
top countries 🇺🇸 United States · 🇨🇦 Canada · 🇩🇪 Germany · 🇮🇳 India · 🇫🇷 France