pith. sign in

Super tiny language models.arXiv preprint arXiv:2405.14159

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.DC 1

years

2026 1 2025 1

representative citing papers

All is Not Lost: LLM Recovery without Checkpoints

cs.DC · 2025-06-18 · conditional · novelty 7.0 · 2 refs

CheckFree recovers intermediate stage failures in pipeline-parallel LLM training via neighbor averaging; CheckFree+ adds out-of-order execution to handle first/last stages by copying neighbors, with small embedding storage, outperforming checkpointing and redundancy at 5-10% failure rates by up to

citing papers explorer

Showing 2 of 2 citing papers.

  • All is Not Lost: LLM Recovery without Checkpoints cs.DC · 2025-06-18 · conditional · none · ref 10 · 2 links

    CheckFree recovers intermediate stage failures in pipeline-parallel LLM training via neighbor averaging; CheckFree+ adds out-of-order execution to handle first/last stages by copying neighbors, with small embedding storage, outperforming checkpointing and redundancy at 5-10% failure rates by up to

  • Stochasticity in Tokenisation Improves Robustness cs.CL · 2026-04-17 · unverdicted · none · ref 10

    Stochastic tokenisation during pre-training and fine-tuning improves LLM robustness to perturbations while preserving accuracy.