Lara Mini explained: a 0.6B-active model for 45 languages
Translated's Lara Mini is a 7.2B mixture-of-experts base model with 0.6B active parameters, trained on 45 languages. Specs, claims, license and who should care.
Tag · moe
Translated's Lara Mini is a 7.2B mixture-of-experts base model with 0.6B active parameters, trained on 45 languages. Specs, claims, license and who should care.
Inkling 2 Small is Thinking Machines' 594B MoE with 17B active parameters, live on Tinker with Apache 2.0 weights promised. Specs, vendor evals and caveats.