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. 👀
> Shrek entropy sampler 
I did some testing with multiple types of models, also with the Llama 1b model. I haven't seen the official benchmarks yet, but improvements are very noticeable even on very small models.
System prompts:
Can you share a link or expand on this? What does the entropy sampler do here?
I think this is the related repo, right nostr:npub1cmmswlckn82se7f2jeftl6ll4szlc6zzh8hrjyyfm9vm3t2afr7svqlr6f ?
What's the Shrek entropy sampler? Is this related to your earlier note? @nostr:nevent1qqsq72y32j707ugtgu26h77marmzrsu0t6dtfpw500q6j49fp3hzckgppemhxue69uhkummn9ekx7mp0qgsvdac80utfn4gvly4fv54la0l6cp0udpptnm3ezzyajkdc44w53lgrqsqqqqqpm0mux9
It's a very early development. Feel free to test it out firsthand. I'll share updates once official benchmarks become available.
OSS for the win 😃
Turns out that people working on things they find interesting is pretty cool 😎
OSS for the win 😃
Turns out that people working on things they find interesting is pretty cool 😎
o1 style chain of thought with a local Llama 1B model (aka shrek sampler) is mostly working...👀
