Stars
A hybrid GPU cluster simulator for ML system performance estimation
Results of Dutch ASR models, collected by the community
Composable AI datacenter simulator designed for hardware procurement and system tuning.
Large-scale VLM pre-training and finetuning 8777 on HPC. Designed and tested for MareNostrum 5 and JUPITER.
Merge of megatron-train, autoexperiment and oellm_pretrain.
Curated Public Repository of LLM (Pre-)Training Data
Codebase for "Machine Unlearning of Personally Identifiable Information in Large Language Models" and the thesis that it built upon : "Toward Practical and Reliable PII Unlearning in Large Language…
Implementation of paper Data Engineering for Scaling Language Models to 128K Context
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
A hierarchical LM that scales to training on context windows of +5M tokens
BPE tokenizer with HuggingFace / SentencePiece
Scripts and instructions for replicating the original FineWeb experiments on LUMI