talkie 1930 13b base
talkie is a 13B vintage language model trained only on pre-1931 English text. It is built to act as a historically grounded conversation partner, with a 1930 knowledge cutoff, and is positioned as the largest vintage language model its creators are aware of.
- Type
- Text
- Weights
- Open
- Likes
- 101
- License
- apache-2.0
Model hub
talkie-lm/talkie-1930-13b-base
- Repo
- talkie-lm/talkie-1930-13b-base
- Access
- Public
Technical tags and languages
More from talkie
3
About talkie
1
Independent AI research lab developing "vintage language models" — LLMs trained exclusively on historical text. Their flagship model, talkie-1930-13b, is a 13B-parameter model trained on 260B tokens of pre-1931 English text (books, newspapers, patents, case law), released under Apache 2.0. The project explores contamination-free generalization, temporal forecasting, and the impact of data diversity on model behavior. Founded by Nick Levine, David Duvenaud, and Alec Radford.