OLMo 2 13B Instruct

Permissive

Allen Institute for AI · OLMo · Released 2024-11

13BText

The larger fully-open OLMo 2 release, giving researchers a reproducible 13B baseline with published data and training code.

Strengths

  • +Apache 2.0 license
  • +Full training transparency for reproducibility research
  • +Improved quality over the 7B tier

Limitations

  • -Smaller ecosystem of fine-tunes and quantizations than Llama/Qwen
  • -Below Qwen2.5-14B on most instruction-following benchmarks

License

Apache 2.0

use commercially with attribution niceties

Hardware

runs on a good consumer GPU (or Apple Silicon) with quantization

Links

Stats

allenai/OLMo-2-1124-13B-Instruct— downloads·— likes

via Hugging Face

Related models