We present YvyrAI, a Spanish-first decoder-only language model architecture centered on a recurrent module called the DeliberationBlock. A shared Transformer block is iterated within a single forward pass while a learned controller maintains a gated planning state, reads and writes a compressed latent scratchpad, re-injects the block input at every step, estimates an internal verification signal, applies a conditional repair update proportional to estimated unreliability, and decides how many iterations to spend before emitting the final hidden representation.
This version (v2.0) reports the first capability-scale training run: a 105.86M-parameter configuration trained from scratch on 891,135,906 tokens of a purpose-built Spanish corpus, using a single consumer GPU with 8 GB of VRAM. Three results are measured. First, recurrent depth helps monotonically: on the same checkpoint, held-out loss falls from 4.2465 at one iteration to 3.8975 at seven, a 29.5% reduction in perplexity (69.86 to 49.28). Second, the benefit saturates exactly at the trained depth, with identical loss from eight to sixteen iterations. Third, the learned halting controller converges to 7.4 of 8 available iterations and stays within 0.0196 nats of the forced-depth curve.
We also report a comparison against GPT-2 124M in bits per character over identical text: 1.3625 for YvyrAI against 2.2238 for GPT-2 on held-out Spanish web text. Beyond the technical contribution, YvyrAI constitutes the first language model architecture developed from first principles by a Latin American research team in the Spanish-speaking world. Weights and inference code are released at Hugging Face under Apache-2.0.