#talkie-lm

The latest AI and developer news about #talkie-lm, with the original source and a short summary.

13B Model Talkie Trained Only on Pre-1931 Data

Talkie, a 13B-scale 'vintage' language model trained solely on historical texts from before 1931, has been released, enabling contamination-free testing of generalization ability.

·2026.04.29 01:00

1930s-Knowledge LLM Released

Revealed the performance and limitations of talkie, a 13B vintage LLM trained on pre-1931 text.

·1·2026.04.28 10:00