Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Answered
Hi Team,

Hi Team, @<1523709867745873920:profile|KindChimpanzee37> @<1523701070390366208:profile|CostlyOstrich36> @<1523701205467926528:profile|AgitatedDove14> @<1523701087100473344:profile|SuccessfulKoala55> I saw Cleargpt video,it is really impressive.but i am having question, Could you respond it?
Are you doing fine tunning on data or do you storing just embedding for it?

  
  
Posted one year ago
Votes Newest

Answers 4


@<1537605940121964544:profile|EnthusiasticShrimp49> ,from this video https://www.google.com/search?q=cleargpt+by+clearml+youtube+video&ei=ipaeZIT6NP3aseM[…]vAOIAZoYkgEJMC4xLjcuMi4xmAEAoAEBwAEByAEC&sclient=gws-wiz-serp i am attaching one snap.could you please tell me are they doing retraining or fine-tunning of model or just storing embedding of files?

  
  
Posted one year ago

Hey @<1533257278776414208:profile|SuperiorCockroach75> , we do both, and much more 🙂

  
  
Posted one year ago

This is doing fine-tuning. Training a multi-billion parameter model from scratch would be economically unfeasible for most of existing enterprises

  
  
Posted one year ago

Ok,Thank you!

  
  
Posted one year ago
967 Views
4 Answers
one year ago
one year ago
Tags