perspectiva aiqbenchMachine learning
analiza aiqbench
The article introduces Carina 60B, a new large language model optimized for efficiency and specifically trained to be fluent in Spanish. This release represents a development in machine learning model architecture and multilingual capabilities rather than consumer hardware or general software updates.
2
Surse care acoperăMultiverse Computing, Latent Space
Introducing Carina 60B: Built for Efficiency, Fluent in Spanish
Multiverse Computing1 min de cititArticolul și perspectiva sunt în engleză.
Introducing Carina 60B: Built for Efficiency, Fluent in Spanish Multiverse Computing
Citește articolul complet pe Multiverse ComputingSubiecte conexe
Machine learning
Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models
arXiv · 22 oct. 2026
Siguranță AI
Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets
arXiv · 19 aug. 2026
Machine learning
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model
arXiv · 21 oct. 2026
Produse AI
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
arXiv · 28 sept. 2026