@kuriko
ML Engineer
Nothing here yet.
Nothing here yet.
14h ago · 16 min read · Introduction As Large Language Models (LLMs) have ballooned to hundreds of billions of parameters, a new challenge has emerged: efficiency. Running a massive model like GPT-4 for every minor task is t
Join discussionFeb 21 · 13 min read · Introduction Training a Large Language Model (LLM) used to require two steps; first, predict the next word; next, rank its answers to fine-tune the behaviors. This second part, known as Reinforcement
Join discussionFeb 12 · 17 min read · Introduction Fine-tuning massive Large Language Models (LLMs) used to require a supercomputer or a cluster of high-end A100 GPUs. For the average developers, this VRAM requirement made the most powerful LLMs untouchable. Quantized Low-Rank Adaptation...
Join discussionFeb 8 · 13 min read · Introduction Data security and infrastructure protection are critical for LLMs and broader Machine Learning (ML) systems. Major cloud providers - AWS, Azure, and Google Cloud - provide Virtual Private Cloud (VPC) necessary to protect sensitive model ...
Join discussion