This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Unsloth AI
unsloth.ai
did:plc:xfbmksnykel6qbq7cs4geveg
For our benchmarks, a standard GRPO QLoRA setup (TRL + FA2) for Llama 3.1 (8B) at 20K context required 510.8GB VRAM. Unsloth’s GRPO algorithms reduces this to just 54.3GB.
The 5GB VRAM requirement for Qwen2.5 (1.5B) is down from 7GB in our previous GRPO release two weeks ago!
2025-02-20T18:41:20.670Z