Llama 3 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 with human preferences for helpfulness and safety.
On-demand deployments give you dedicated GPUs for Llama 3 8B using Fireworks' reliable, high-performance system with no rate limits.
Learn MoreMeta
8192
$0.2
