- StableLM Web Demo
- Microsoft’s LLMA Accelerates LLM Generations via an ‘Inference-With-Reference’ Decoding Approach
- Understanding Parameter-Efficient Finetuning of Large Language Models: From Prefix Tuning to LLaMA-Adapters
- Prompt Reducer - Cut Down GPT-4 Token Costs
- Microsoft Loop: Collaborative App | Microsoft 365