Mid-size: 10 to 70 billion
The workhorse open models: Llama 2 13B, Qwen 32B, Gemma 27B and their kin. 103 models.
🇺🇸 United StatesTuring-NLG
Microsoft's 17-billion-parameter Transformer model for generation, QA and summarisationGeneral · Research only · 2020
🇺🇸 United StatesBloombergGPT
A 50 billion parameter language model for finance.Domain · Research only · 2023
🇰🇷 South KoreaEXAONE 3.5
LG AI Research open language model series for real-world tasksGeneral · Conditional licence · 2024