talkie-lm/talkie-1930-13b-it
Summary
Talkie-1930-13b-it is a 13B parameter instruction-tuned language model trained on pre-1931 text and fine-tuned using reinforcement learning with DPO.
View Cached Full Text
Cached at: 05/08/26, 09:06 AM
talkie-lm/talkie-1930-13b-it · Hugging Face
Source: https://huggingface.co/talkie-lm/talkie-1930-13b-it 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 ourreport.
Reference code to run talkie is available onGitHub.
Similar Articles
Pretraining Language Models on Historical Text
This paper introduces TypewriterLM, a 7.24B parameter language model trained exclusively on English text predating 1913, along with TypewriterCorpus (a 54B-token cleaned historical corpus) and instruction-tuning datasets to avoid temporal leakage and lookahead bias. It also presents a benchmark suite, History-Event, for evaluating temporal grounding and leakage.
Higgs Audio v3 TTS 4B. Built for voice chat. Support 100 languages and inline control.
Higgs Audio v3 is a 4B parameter TTS model designed for voice chat applications, supporting 100 languages with inline control capabilities.
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
This paper proposes Badit, a method that decomposes large language model parameters into orthogonal high-singular-value LoRA experts to mitigate cross-task interference during multi-task instruction tuning.
dots.tts 2B🎙️ SOTA TTS from RedNote
RedNote releases dots.tts, a 2B parameter open-source text-to-speech model with zero-shot voice cloning and 48 kHz synthesis.
dots.tts Technical Report
dots.tts presents a 2B-parameter continuous autoregressive TTS model trained on multilingual data, achieving state-of-the-art performance on benchmarks like Seed-TTS-Eval with low-latency streaming via CFG-aware MeanFlow distillation. The model, code, and checkpoints are released under Apache 2.0.