“lora”

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs

Chinese LLaMA & Alpaca大语言模型+本地CPU/GPU训练部署

Agent Reinforcement Trainer

20+ high-performance LLMs with recipes to pretrain, finetune, and deploy at scale.