Downloads · 30 days
0
anotheruserishere/talkie-1930-13b-it
talkie-1930-13b-it is a machine learning model from anotheruserishere. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
talkie-1930-13b-it is a 13B vintage language model. It is an instruction-tuned post-train of talkie-1930-13b-base, which was trained on 260B tokens of pre-1931 English-language text.
Downloads · 30 days
0
Access
Public
Updated May 27, 2026
Repo size
26.6 GB
Likes
0
Public
Click a slice to open those files.
.pt26.6 GB · 100%
From the Hugging Face model README
talkie-1930-13b-it is a 13B vintage language model. It is an instruction-tuned post-train of talkie-1930-13b-base, which was trained on 260B tokens of pre-1931 English-language text.
talkie-1930-13b-it was finetuned using a novel dataset of instruction-response pairs extracted from pre-1931 reference works, including etiquette manuals, encyclopedias, and letter-writing manuals. The model then underwent reinforcement learning (online DPO with an LLM-as-a-judge) to improve instruction-following ability.
Read more about talkie in our report.
Reference code to run talkie is available on GitHub.