Atlas

Models

← All models

Stable Beluga 2

Stability AI · 2023-07-20 · 69B parameters

Stable Beluga 2 is Stability AI's instruction-tuned derivative of Meta's Llama 2 70B, fine-tuned using Stability AI’s internal Orca-style synthetic dataset derived from conceptofmind datasets created by Enrico Shippole to improve multi-step reasoning and instruction-following quality. Released in July 2023, it was among the strongest openly available 70B chat models at the time, demonstrating that Orca-style training could substantially enhance the capability of Llama 2 base models. The model is available on Hugging Face under Stability AI's separate non-commercial community license.

Benchmark scores

BenchmarkScore
BBH (Open LLM Leaderboard v2)58.2
Capability110.7
Epoch Capabilities Index (ECI)116
GPQA (Open LLM Leaderboard v2)31.6
IFEval (Open LLM Leaderboard v2)37.9
MATH Level 5 (Open LLM Leaderboard v2)4.4
MMLU-Pro (Open LLM Leaderboard v2)33.3
MuSR (Open LLM Leaderboard v2)47.3
Loading Atlas data…