Abstract:This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd context including the previewed Behemoth teacher model, (ii) architectural characteristics beyond a high-level MoE description covering routed/shared-expert structure, early-fusion multimodality, and long-context design elements reported for Scout (iRoPE and length generalization strategies), (iii) training disclosures spanning pre-training, mid-training for long-context extension, and post-training methodology (lightweight SFT, online RL, and lightweight DPO) as described in release materials, (iv) developer-reported benchmark results for both base and instruction-tuned checkpoints, and (v) practical deployment constraints observed across major serving environments, including provider-specific context limits and quantization packaging. The manuscript also summarizes licensing obligations relevant to redistribution and derivative naming, and reviews publicly described safeguards and evaluation practices. The goal is to provide a compact technical reference for researchers and practitioners who need precise, source-backed facts about Llama 4.



Abstract:Content based data classification is an open challenge. Traditional Data Loss Prevention (DLP)-like systems solve this problem by fingerprinting the data in question and monitoring endpoints for the fingerprinted data. With a large number of constantly changing data assets in Facebook, this approach is both not scalable and ineffective in discovering what data is where. This paper is about an end-to-end system built to detect sensitive semantic types within Facebook at scale and enforce data retention and access controls automatically. The approach described here is our first end-to-end privacy system that attempts to solve this problem by incorporating data signals, machine learning, and traditional fingerprinting techniques to map out and classify all data within Facebook. The described system is in production achieving a 0.9+ average F2 scores across various privacy classes while handling a large number of data assets across dozens of data stores.