https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://purl.org/dc/terms/creator creator

https://w3id.org/np/RAoSadUw99... RAoSadUw99

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its provenance http://www.nanopub.org/nschema#hasProvenance provenance

http://www.w3.org/ns/prov#wasAttributedTo wasAttributedTo

https://w3id.org/np/RAoSadUw99... RAoSadUw99

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its provenance http://www.nanopub.org/nschema#hasProvenance provenance

http://www.w3.org/ns/prov#wasAttributedTo wasAttributedTo

https://orcid.org/0000-0002-0085-6496 0000-0002-0085-6496

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://www.w3.org/2000/01/rdf-schema#comment comment

You only learn a few parameters, with your parameter "efficient" finetuning. The rest is💩 A whole line of works🧵 shows that by throwing redundancy we can get better LoRas, keep less memory and of course model merge https://twitter.com/LChoshen/status/1833879920348422216/photo/1 ComPeft shows you can improve LoRAs by pruning aggressively and making the remaining weights binary (+/-) It also means parameter efficiency still relies on overparametrization(but only during training) https://x.com/prateeky2806/status/1727589818618523783 Laser shows it on full models https://x.com/pratyusha_PS/status/1739025292805468212 https://twitter.com/LChoshen/status/1833879922500080084/photo/1 In merging, many find that with only those few weights one can make a "multitask" model, keeping the important ones for each model and switching. those e.g. 1% of the weights also represent tasks well Many.. https://www.alphaxiv.org/abs/2408.13656 https://www.alphaxiv.org/pdf/2405.07813 https://www.alphaxiv.org/pdf/2310.01886 Those works are focused on efficient multitask learning that compresses the models, can keep many models and switch between them as necessary. Another option to compress is to SVD the LORA, separately or to a shared space, saving the tiny differences https://x.com/RickardGabriels/status/1810368375455207470 And just because we discussed compression, of course this is all just "model compression" if you want to compress to just save space, there are smarter ways: https://github.com/zipnn/zipnn

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

https://schema.org/keywords keywords

finetuning

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

https://schema.org/keywords keywords

low-rank-adapters

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

https://schema.org/keywords keywords

model-compression

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

https://schema.org/keywords keywords

multitask-learning

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

https://schema.org/keywords keywords

serving-systems

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

https://sense-nets.xyz/endorses endorses

https://www.arxiv.org/abs/2407.00066 2407.00066

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its provenance http://www.nanopub.org/nschema#hasProvenance provenance

http://www.w3.org/ns/prov#wasGeneratedBy wasGeneratedBy

https://w3id.org/np/RAszCcnWVT...#activity activity

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://purl.org/spar/cito/discusses discusses

https://x.com/prateeky2806/status/1727589818618523783 status/1727589818618523783

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://purl.org/spar/cito/discusses discusses

https://www.alphaxiv.org/abs/2408.13656 2408.13656

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://purl.org/spar/cito/discusses discusses

https://www.alphaxiv.org/pdf/2310.01886 2310.01886

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://purl.org/spar/cito/discusses discusses

https://www.alphaxiv.org/pdf/2405.07813 2405.07813

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://purl.org/spar/cito/agreesWith agreesWith

https://x.com/RickardGabriels/status/1810368375455207470 status/1810368375455207470

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://purl.org/spar/cito/agreesWith agreesWith

https://x.com/pratyusha_PS/status/1739025292805468212 status/1739025292805468212

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://purl.org/spar/cito/includesQuotationFrom includesQuotationFrom

https://x.com/RickardGabriels/status/1810368375455207470 status/1810368375455207470

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

http://purl.org/spar/cito/includesQuotationFrom includesQuotationFrom

https://x.com/pratyusha_PS/status/1739025292805468212 status/1739025292805468212

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

https://sense-nets.xyz/recommends recommends

https://github.com/zipnn/zipnn zipnn

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its provenance http://www.nanopub.org/nschema#hasProvenance provenance

http://www.w3.org/ns/prov#wasAssociatedWith wasAssociatedWith

https://x.com/LChoshen LChoshen

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its provenance http://www.nanopub.org/nschema#hasProvenance provenance

http://www.w3.org/ns/prov#linksTo linksTo

https://x.com/LChoshen/status/1833879920348422216 status/1833879920348422216

Sensenets

2024-09-11T18:07:24.837Z

https://w3id.org/np/RAszCcnWVT... RAszCcnWVT

links a nanopublication to its assertion http://www.nanopub.org/nschema#hasAssertion assertion

https://sense-nets.xyz/summarizes summarizes

https://www.arxiv.org/abs/2407.00066 2407.00066

Sensenets

2024-09-11T18:07:24.837Z