HLAT: High-quality Large Language Model Pre-trained on AWS Trainium

Documenti analoghi

• NeuronMLP: Efficient LLM Inference via Singular Value Decomposition Compression and Tiling on AWS Trainium
  di: Song, Dinghong, et al.
  Pubblicazione: (2025)
• NinjaLLM: Fast, Scalable and Cost-effective RAG using Amazon SageMaker and AWS Trainium and Inferentia2
  di: Xue, Tengfei, et al.
  Pubblicazione: (2024)
• Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
  di: Gautam, Tanmay, et al.
  Pubblicazione: (2024)
• Pre-trained Large Language Models Use Fourier Features to Compute Addition
  di: Zhou, Tianyi, et al.
  Pubblicazione: (2024)
• CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models
  di: Yu, Hao, et al.
  Pubblicazione: (2023)