This is a merge of pre-trained language models created using mergekit. An experimental merge of LoRa adapter to further boost Shisa-K-12B roleplaying capabilities with essence of PocketDoc/Dans-SakuraKaze-V1.0.0-12b. Can occasionaly output japanese symbols, potentially mitigated by lowering TOPP to 90 and increasing MINP to 0.1. Oh, and I am planning to use this model as layer range for next KansenSakura update This model was merged using the Linear merge method using ./retokenized_SHK as a base. The following models were included in the merge: ./retokenizedSHK + ./lora_Dans-SakuraKaze-V1.0.0-12b-64d The following YAML configuration was used to produce this model:
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Retreatcost
Теги: mistral, mergekit, merge, conversational, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 27
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
