L20-Edu-135M: An Auditable Single-GPU Study of Data-Efficient Small Language Modeling

• URL: http://arxiv.org/abs/2606.22189v1
• Date: Sat, 20 Jun 2026 18:42:37 GMT
• Title: L20-Edu-135M: An Auditable Single-GPU Study of Data-Efficient Small Language Modeling
• Abstract summary: Small language models are cheap to serve and feasible on local hardware.<n>Strong public 135M-class systems are commonly trained with hundreds of billions to trillions of tokens on large clusters.
• Score: 6.901585308625979
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Small language models are cheap to serve and feasible on local hardware, but strong public 135M-class systems are commonly trained with hundreds of billions to trillions of tokens on large clusters. We study a sharply resource-constrained regime: a complete 134.5M-parameter language-model pipeline executed on one NVIDIA L20 GPU. The released checkpoint, L20-Edu-135M, receives approximately 13B pretraining tokens: 10B FineWeb-Edu tokens followed by a 3B-token educational, mathematics, code, and reasoning mixture. We document the architecture, data gates, cross-source MinHash/LSH near-deduplication, segment deduplication, benchmark-overlap removal, throughput optimization, supervised fine-tuning (SFT) with weight interpolation, and reinforcement learning from verifiable rewards (RLVR) on GSM8K. In a self-run zero-shot six-task harness, L20-Edu-135M obtains a mean score of 0.4150. It trails SmolLM-135M (0.4767) and SmolLM2-135M (0.4917), but its mean is 87.1% of SmolLM-135M's while its nominal token count is 2.17% as large. This ratio is descriptive, not evidence of statistical equivalence or a controlled scaling law. The model exceeds several older 100M-160M public baselines under the same harness. Direct GRPO-style RLVR decreases GSM8K exact-match accuracy from 1.82% to 1.59% (192-token completions) and 1.21% (320-token completions). These single-run results identify a concrete failure mode rather than establishing a general lower bound on RLVR. The contribution is an auditable resource-constrained case study, not a state-of-the-art claim.

Related papers

• Breaking the Token Ceiling: Distilling Smaller, Stronger Byte Models [67.72077328700088]
  We present the first large scale study of overtraining decoder-only dense transformer models varying two dimensions simultaneously.<n>We find that Token-1B models outperform byte models (End-Of-Token-1B and Bytes-1B) in the low-FLOP regime but eventually plateau.<n>By operating over a small vocabulary of 256 bytes instead of on the order of 100K tokens, they circumvent the need for top-kruncation during logit dumping.
  arXiv  Detail & Related papers  (2026-09-11T00:17:22Z)
• Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference [0.0]
  Small language models are usually built like large ones and then squeezed onto a CPU afterwards.<n>We did the opposite: we fixed the target first, one user, one token at a time, 4-bit weights, ordinary CPU, and chose the architecture to suit it.<n>The model scores 47.31 on a five-task benchmark against a bar of 42.20 that was fixed before training began.<n>It beats GPT-2 124M, Pythia-160M, OPT-125M and GPT-neo-125M, all trained on three to six times more data, and exceeds MobileLLM-125M'
  arXiv  Detail & Related papers  (2026-08-20T16:09:43Z)
• A Sovereign, Open-Source Foundation Model for German and English [50.08096276509294]
  Soofi S 30B-A3B is a sovereign, open-source Mamba Transformer foundation model for German and English.<n>Its hybrid design activates only 3B of 30B parameters per token and keeps the inference cache near-constant as context grows.
  arXiv  Detail & Related papers  (2026-07-10T13:51:41Z)
• Surpassing Scale by Efficiency: A Compact 135M Parameter Foundational LLM Natively Adapted for the Bangla Language [0.8594140167290097]
  This paper presents bangla-smollm-135m, a 135-million parameter decoder-only foundational model engineered explicitly for high-efficiency language modeling in the Bangla script.<n>By leveraging a deterministic intersect-and-append token merging strategy, the model overcomes subword script fragmentation without destabilizing early pretrained parameter states.
  arXiv  Detail & Related papers  (2026-06-15T08:16:52Z)
• Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study [0.0]
  Cross-architecture evaluation of production LLM inference on AMD Instinct MI325X GPUs.<n> benchmarking four models spanning 235B to 1 trillion parameters across three architectural families.
  arXiv  Detail & Related papers  (2026-02-27T13:21:48Z)
• Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model [100.86587937568832]
  Ring-1T is the first open-source, state-of-the-art thinking model with a trillion-scale parameter.<n>It features 1 trillion total parameters and activates approximately 50 billion per token.
  arXiv  Detail & Related papers  (2025-10-21T17:46:14Z)
• LaSeR: Reinforcement Learning with Last-Token Self-Rewarding [54.72617309922891]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency.<n>We propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss.
  arXiv  Detail & Related papers  (2025-10-16T17:55:11Z)
• MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes [60.57770396565211]
  We show that strong reasoning abilities can emerge with far less data.<n>MobileLLM-R50M achieves an AIME score of 15.5, compared to just 0.6 for OLMo-2-1.48B and 0.3 for SmolLM-2-1.7B.
  arXiv  Detail & Related papers  (2025-09-29T15:43:59Z)
• Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models [43.98994504606355]
  We propose Reinforcement Learning via Self-Confidence (RLSC) for large language models (LLMs)<n>RLSC uses the model's own confidence as reward signals-eliminating the need for labels, preference models, or reward engineering.
  arXiv  Detail & Related papers  (2025-06-05T19:55:15Z)
• Language models scale reliably with over-training and on downstream tasks [121.69867718185125]
  Scaling laws are useful guides for derisking expensive training runs. However, there remain gaps between current studies and how language models are trained. In contrast, scaling laws mostly predict loss on inference, but models are usually compared on downstream task performance.
  arXiv  Detail & Related papers  (2024-03-13T13:54:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.