openbmb/Ultra-FineWeb-L1
Viewer • Updated • 1.14B • 20.7k • 177
This model was asked to be published under my account, not the creators. The compute came from https://huggingface.co/posts/ProCreations/855858308074329
Chat fine-tune of ProCreations/boopit-1: the same 1.58-bit ternary 28M / 4096-context model, SFT'd on mookiezi/Discord-Dialogues.
Packed weights stay under 7MB.
Prompt: <bos> your message <sep> and sample until <eos>.
Base model
ProCreations/boopit-1