A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and «flavor» of the resulting model. Version notes for 0.2: Basically, reprocessed the whole dataset again, due to a severe mistake in previously used pipeline, which left the data poisoned with a lot of non-unicode characters. Now, no more weird generation artifacts, and more stability. Major kudos to Cahvay for his work on fixing this critical issue. Prompt format is ChatML. Recommended sampler values: Temperature: 1 Min-P: 0.05 Top-A: 0.2 Repetition Penalty: 1.03 Recommended SillyTavern presets (via CalamitousFelicitousness): Training data: Celeste 70B 0.1 data mixture minus Opus Instruct subset. See that model’s card for details. Kalomaze’s OpusInstruct25k dataset, filtered for refusals. A subset (1k rows) of ChatGPT-4o-WritingPrompts by Gryphe A subset (2k rows) of Sonnet3.5-Charcards-Roleplay by Gryphe Synthstruct and SynthRP datasets by Epiculous A subset from Dolphin-2.9.3, including filtered version of not_samantha and a small subset of systemchat. Training…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: waldie
Теги: qwen2, generated_from_trainer, conversational, text-generation-inference, endpoints_compatible, 4-bit, exl2
Лайков: 3 | Загрузок: 9
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
