Deployed via NVIDIA NIM to fine-tune Llama 3.1 using a PEFT technique called LoRA using the NVIDIA Nemo Framework.
Features
- Speed: Fastest production level inference speeds
- Generate Answers: Generate accurate, context specific end answers based on law dataset
- Auto Expire: Automatically expire and delete data after a certain time
Original
Result
Built with
- Next.js
- tailwindcss
- Deployed on Vercel
- Data stored on Upstash