Framework and no-code GUI for fine-tuning LLMs
Vertically Unified Agents for Graph Retrieval-Augmented Reasoning
slime is an LLM post-training framework for RL Scaling
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs
Unified KV Cache Compression Methods for Auto-Regressive Models
Build multimodal language agents for fast prototype and production
Tools for merging pretrained large language models
Constrained Value Alignment via Safe Reinforcement Learning
MemoryOS is designed to provide a memory operating system