This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Wolfram Ravenwolf
wolfram.ravenwolf.ai
did:plc:k7c63zbro5iekhqjhvqag4ea
Almost done benchmarking, write-up coming tomorrow – but wanted to share some important findings right away: Tested QwQ from 3 to 8 bit EXL2 in MMLU-Pro, and by raising max_tokens from default 2K to 8K, smaller quants got MUCH better scores. They need room to think!
[contains quote post or other embedded content]
2024-12-01T23:50:10.655Z