Global Feed Post Login
Replying to Avatar iefan 🕊️

Lol, did the open-source community accidentally just fix the LLM hallucination problem? 😳

Context:

It seems like the Shrek entropy sampler with early exit solves, if not significantly reduces, the hallucination problem with big boy models. Some people are running evaluations now, and so far, it seems promising. 👀

Avatar
iefan 🕊️ 1y ago

o1 style chain of thought with a local Llama 1B model (aka shrek sampler) is mostly working...👀

nostr:nevent1qqstp7xa22u8r4kphv65dcx52nv0q63lsq0axdrrgshf3yvvpgd5u3gpzamhxue69uhhyetvv9ujuvrcvd5xzapwvdhk6tczyrr0wpmlz6va2r8e92t990ltl7kqtlrgg2u7uwgs38v4nw9dt4y06qcyqqqqqqgn6ylz8

Reply to this note

Please Login to reply.

Discussion

No replies yet.