Open-weight language models in 2022
15
Models
10 organisations
100%
Open weights
15 open, 0 closed
0
Frontier
By Epoch's flag
176B
Largest traceable
BLOOM-176B
2022
Span
8 with a traceable size
Releases
by monthOrganisation
Country
Records
15| Model | Organisation | Released | Parameters | Weights |
|---|---|---|---|---|
| Hybrid H3-2.7B | Stanford University | 2022-12 | 3B * | Open |
| Galactica | Meta AI | 2022-11 | 120B * | Open |
| mT0-13B | Hugging Face | 2022-11 | 13B | Open |
| BlenderBot 3 | McGill University | 2022-08 | 175B * | Open |
| GLM-130B | Tsinghua University | 2022-08 | 130B | Open |
| BLOOM-176B | Hugging Face | 2022-07 | 176B | Open |
| CodeT5-large | Salesforce | 2022-07 | 770M * | Open |
| NLLB | Meta AI | 2022-07 | 55B | Open |
| GPT-2 Medium (FlashAttention) | Stanford University | 2022-05 | 355M | Open |
| OPT-175B | Meta AI | 2022-05 | 175B | Open |
| SimCSE | Princeton University | 2022-05 | — | Open |
| UL2 | Google Research | 2022-05 | 20B | Open |
| GPT-NeoX-20B | EleutherAI | 2022-02 | 20B | Open |
| PolyCoder | Carnegie Mellon University (CMU) | 2022-02 | 3B * | Open |
| data2vec (language) | Meta AI | 2022-01 | 705M * | Open |
An asterisk marks a parameter figure the source does not consider traceable to the people who built the model. That judgement is the source’s and it has false negatives: Kimi K3 is marked speculative at 2.8T while Moonshot’s own model card states the figure. Why that distinction carries the whole exhibit.
Counts are of models Epoch AI records as notable, not of every model released. The most recent month is always incomplete, because a model enters the dataset when it is reviewed rather than when it ships.
Epoch AI, 'Data on AI Models'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/data/ai-models-documentation' Used under CC BY 4.0.