cs.LGAug 3, 2026

Wiring Beats Blending: What Transfers Between Transformer Sizes -- and What Doesn't

Authors: Ravi Satya Durga Prasad Yenugula

Abstract

Model families are typically trained size by size, each from scratch. Can apretrained large model instead be converted into a smaller sibling? Wecharacterize the 1.4B->410M conversion in the Pythia family end to end.Representations align strongly across sizes (ridge R^2=0.84) while parametersalign weakly. Dense weight projection is functionally destructive, and abit-exact reconstruction control shows this is not an assembly artifact: basismixing breaks rotary, per-head, GELU, and LayerNorm structure. After the best-fitlinear operator, weight residuals are statistically indistinguishable from noiseunder shuffle controls. Conversion value therefore lives in initialization. Inmatched-budget continued pre-training we decompose conversion into twoindependent levers: least-squares compensation (a function lever, best zero-shot)and variance-preserving rescale (a dynamics lever, best endpoints). Compensationis a token-efficient, low-budget win rather than a universal one. At 30M tokens itbeats the strongest subcloning variant on both a width-reduced pair (84.0 +/- 1.8vs. 89.7 +/- 3.7, 3/3 seeds) and a held-out depth-reduced pair (109.3 vs. 117.9,3/3 seeds), reaching a given quality with fewer tokens. At a 33x larger budget thetwo converge to parity (40.0 vs. 40.0), both far ahead of from-scratch, whichtransfer initialization always beats: by up to 18x at low budget, with the marginnarrowing at convergence and at the largest scale. We also map the method'sboundary. At about 5x the donor scale (6.9B->1.4B) stacking both leversover-corrects, consistent with ill-conditioning of the compensation solve at largewidth, which points to dimension-aware regularization as a fix. At matched budgetour initialization also beats structured pruning with distillation, the standardpipeline for this task, and improves further when combined with it. Code,checkpoints, and the frozen evaluation corpus are released.

Explore similar work

CardsList
Sep 14, 2026cs.CL

Breaking the Token Ceiling: Distilling Smaller, Stronger Byte Models

Small models are made more capable through distillation from a larger one that shares their tokenization scheme. However, do distilled byte and token models behave similarly in terms of scaling trends as compute and data increases? To enable this comparison, we introduce two variants to efficiently convert token logits to Byte Logits: 1) approximate: Marginalize-It, and 2) exact: End-Of-Token. We then present the first large scale study of overtraining decoder-only dense transformer models varying two dimensions simultaneously: the tokenization scheme (Tokens, Bytes, Bytes w/ eot) and the training objective (Distillation vs. Cross-Entropy), sweeping layer-parameter-matched models with roughly 1 billion parameters up to 1 trillion bytes of data. Across eight benchmarks spanning three categories: Multiple Choice QA, Language Generation, and Machine Translation, we find that Token-1B models outperform byte models (End-Of-Token-1B and Bytes-1B) in the low-FLOP regime but eventually plateau; byte models start worse yet surpass Token-1B models with more compute, reaching a higher downstream task performance ceiling. Extrapolating the average top-1 error vs. validation BPB scaling laws predicts that, asymptotically, distilled End-Of-Token-1B outperforms distilled Token-1B by up to 4%. They are also far more data efficient, matching the performance of distilled Token-1B using only one-sixth of the training data. Moreover, by operating over a small vocabulary of 256 bytes instead of on the order of 100K tokens, they circumvent the need for top-k truncation during logit dumping, while also reducing logit storage costs to roughly one-fifth. Finally, our downstream performance scaling laws predict that our distilled End-Of-Token-1B models asymptotically surpass the Llama 3.2-1B, Gemma-3-1B-pt, and Gemma 2B models on averaged downstream tasks by up to 6.5%, 8.1%, and 2.1%, respectively.
Kalyani Marathe, Artidoro Pagnoni, Tomasz Limisiewicz +4
Large Language Model ScaleByte-Pair EncodingDataset Distillation
AskPDF
Jun 12, 2026cs.LG

Small LLMs: Pruning vs. Training from Scratch

Pruning promises a shortcut to strong small language models. In this work, we examine this promise by pruning Llama-3.1-8B at pruning ratios of 0.5--0.8 with six methods spanning depth, width, and sparse granularities, under two controlled token-matched settings. (1) With the same training token budget, pruned initialization consistently outperforms random initialization. This shows that the parent model provides a strong starting point, although the advantage narrows as the training token budget grows and as the pruning ratio rises, nearly vanishing at the highest pruning ratio we study. (2) When training from scratch is instead given the full token budget consumed by the whole pipeline, pruning at finer granularities still retains an advantage, while coarser structured pruning can be matched or surpassed. This suggests that the parent model transfers knowledge that additional training tokens alone cannot fully recover, but only at fine granularity. Taken together, our results yield a clear recommendation: with a large pretrained model in hand and a limited training token budget, pruning is better than training from scratch; when the training budget is not limited, training from scratch can be competitive for coarser pruning, so a large pretrained parent is not always necessary.
Yufeng Xu, Taiming Lu, Kunjun Li +3
Small Large Language ModelsStructured PruningBudgetsScratch
AskPDF
Apr 16, 2026cs.LG

Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization

The pre-training and fine-tuning paradigm has become the dominant approach for model adaptation. However, conventional pre-training typically yields models at a fixed scale, whereas practical deployment often requires models of varying sizes, exposing its limitations when target model scales differ from those used during pre-training. To address this, we propose an innovative constraint-based pre-training paradigm that imposes structured constraints during pre-training to disentangle size-agnostic knowledge into reusable weight templates, while assigning size-specific adaptation to lightweight weight scalers, thereby reformulating variable-sized model initialization as a multi-task adaptation problem. Within this paradigm, we further introduce WeiT, which employs Kronecker-based constraints to regularize the pre-training process. Specifically, model parameters are represented as compositions of weight templates via concatenation and weighted aggregation, with adaptive connections governed by lightweight weight scalers whose parameters are learned from limited data. This design enables flexible and efficient construction of model weights across diverse downstream scales. Extensive experiments demonstrate the efficiency and effectiveness of WeiT, achieving state-of-the-art performance in initializing models with varying depths and widths across a broad range of perception and embodied learning tasks, including Image Classification, Image Generation, and Embodied Control. Moreover, its effectiveness generalizes to both Transformer-based and Convolution-based architectures, consistently enabling faster convergence and improved performance even under full training.
Fu Feng, Yucheng Xie, Ruixiao Shi +2
Model PretrainingParameter-Efficient AdaptationModel WeightsConvolutional Neural Networks
AskPDF