Llama 2 70B Chat

Meta

The flagship, 70 billion parameter language model from Meta, fine tuned for chat completions. Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.

ANALYSIS STATUS

No analysis yet

This model exists in our database, but we only publish political alignment results once its full analysis run is completed.

A full run currently requires 114 completed bill analyses.