Tagged "efficient-training"

3 articles tagged efficient-training, 14 February 2026 to 23 February 2026. Newest first.

• Wave Field LLM Achieves O(n log n) Scaling: 825M Model Trained to 1B Parameters in 13 Hours 23 February 2026

  Wave Field LLM v4 demonstrates efficient pretraining architecture, reaching 1 billion parameter scale with 825M actual parameters trained on 1.33B tokens in just 13.2 hours, showing significant progress toward resource-efficient model training.

• CPU-Trained Language Model Outperforms GPU Baseline After 40 Hours 22 February 2026

  A developer successfully trained FlashLM v5 'Thunderbolt' on CPU hardware, achieving a 1.36 perplexity with just 29.7M parameters and beating established GPU baselines. This demonstrates the viability of efficient CPU-based model training for resource-constrained environments.

• GPT-OSS 120B Uncensored Model Released in Native MXFP4 Precision 14 February 2026

  An uncensored version of GPT-OSS 120B has been released featuring native MXFP4 precision training, offering 117B parameters with MoE architecture for efficient local deployment.