The AI Museum
AI Analytics1,072 recordsRecounted 23 September 2026

Open-weight language models in 2019

18

Models

13 organisations

100%

Open weights

18 open, 0 closed

5

Frontier

By Epoch's flag

11B

Largest traceable

T5-11B

2019

Span

12 with a traceable size

Releases

by month
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sept
Oct
Nov
Dec

Records

18
Open-weight language models in 2019, newest first. Each row links to the source Epoch AI records for it.
ModelOrganisationReleasedParametersWeights
CamemBERTFacebook2019-11335MOpen
XLM-RoBERTaFacebook AI2019-11550MOpen
BART-largeFacebook AI2019-10406M *Open
DistilBERTHugging Face2019-1066MOpen
T5-11BGoogle2019-1011BOpen
T5-3BGoogle2019-103BOpen
Adaptive Inputs + LayerDropFacebook AI Research2019-09423MOpen
ALBERTToyota Technological Institute at Chicago2019-0918MOpen
RoBERTa LargeFacebook2019-07355MOpen
AWD-LSTM + MoS + Partial ShuffledUniversity of Texas at Austin2019-0635MOpen
XLMFacebook2019-06665M *Open
XLNetCarnegie Mellon University (CMU)2019-06340MOpen
AWD-LSTM-DRILL + dynamic evaluation† (WT2)IDIAP2019-0534M *Open
Cross-lingual alignmentTel Aviv University2019-04Open
SciBERTAllen Institute for AI2019-03110MOpen
GPT-2 (1.5B)OpenAI2019-022B *Open
MT-DNNMicrosoft2019-01330MOpen
Transformer-XL (257M)Carnegie Mellon University (CMU)2019-01257M *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.

How this museum is made