Reasoning without the token cost: 32 LatentMT LoRA adapters that think in hidden states, covering DRT, ArzEnMultiGenre, and 30 Flores200 pairs.
Wei Rui Chen
wrchen1
AI & ML interests
None yet
Recent Activity
updated a collection about 20 hours ago
LatentMT published a model about 20 hours ago
wrchen1/LatentMT-2.6B-eng-latn-vec-latn updated a model about 20 hours ago
wrchen1/LatentMT-2.6B-eng-latn-vec-latnOrganizations
models 32
wrchen1/LatentMT-2.6B-eng-latn-vec-latn
Text Generation • Updated • 6
wrchen1/LatentMT-2.6B-eng-latn-taq-tfng
Text Generation • Updated • 6
wrchen1/LatentMT-2.6B-eng-latn-taq-latn
Text Generation • Updated • 3
wrchen1/LatentMT-2.6B-eng-latn-szl-latn
Text Generation • Updated • 5
wrchen1/LatentMT-2.6B-eng-latn-srd-latn
Text Generation • Updated • 5
wrchen1/LatentMT-2.6B-eng-latn-shn-mymr
Text Generation • Updated • 7
wrchen1/LatentMT-2.6B-eng-latn-prs-arab
Text Generation • Updated • 3
wrchen1/LatentMT-2.6B-eng-latn-pbt-arab
Text Generation • Updated • 7
wrchen1/LatentMT-2.6B-eng-latn-nus-latn
Text Generation • Updated • 6
wrchen1/LatentMT-2.6B-eng-latn-mni-beng
Text Generation • Updated • 9
datasets 0
None public yet