Language models from Stanford University
12
Models
1 organisations
50%
Open weights
4 open, 4 closed
0
Frontier
By Epoch's flag
3B
Largest traceable
DPO on Pythia-2.8B
2003–2023
Span
4 with a traceable size
Organisation
Country
Records
12| Model | Organisation | Released | Parameters | Weights |
|---|---|---|---|---|
| GPT3-2.7B (FlashAttention-2) | Stanford University | 2023-07 | 3B | Closed |
| DPO on Pythia-2.8B | Stanford University | 2023-05 | 3B | Closed |
| Hybrid H3-2.7B | Stanford University | 2022-12 | 3B * | Open |
| GPT-2 Medium (FlashAttention) | Stanford University | 2022-05 | 355M | Open |
| S4 | Stanford University | 2021-10 | 249M * | Open |
| ELECTRA | Stanford University | 2020-03 | 335M * | Open |
| Base LM + kNN LM + Continuous Cache | Stanford University | 2019-11 | 247M * | Closed |
| GloVe (32B) | Stanford University | 2014-01 | 120M * | Not recorded |
| GloVe (6B) | Stanford University | 2014-01 | 120M * | Not recorded |
| RNTN | Stanford University | 2013-10 | — | Closed |
| Vector Space Model | Stanford University | 2011-06 | 255,000 | Not recorded |
| LDA | Stanford University | 2003-02 | — | Not recorded |
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.