Tagged: llm-training

6 articles

Latest

IBM's Granite 4.2 trains on 15T tokens and learns to code inside real sandboxes

BigCode's dedupe method cuts training data bloat by up to 40%

Kids Master Language on 100M Words; GPT-2 Needs Billions and Still Babbles

Llama 2 70B fine-tuning slashes RAM from 2TB to 32GB with FSDP trick

Microsoft Drops DIFF Transformer V2, Fixing the 100x Instability That Sank V1

ServiceNow drops SyGra, a free framework to stop your AI dataset nightmares