This is a merge of pre-trained language models created using mergekit. This model was tested using text-generation-webui. I use preset minp and Null preset` with temperature=0.3 for Generation. This format must be adhered to strictly, as deviations may result in less optimal outputs from the model. The template used to construct a prompt for the Instruct model is specified as follows: Please be aware that and are special tokens used for the beginning of string (BOS) and end of string (EOS), respectively, while [INST] and [/INST] are considered regular strings. For the «{SYSTEM_PROMPT}» part, We recommend using «あなたは日本語を話す優秀なアシスタントです。回答には必ず日本語で答えてください。また考える過程も出力してください。» For the «{USERMESSAGE1}» part, We recommend using {instruction}n{input} This model was merged using the Model Stock merge method using nitky/Oumuamua-7b-base as a base. The following models were included in the merge: stabilityai/japanese-stablelm-base-gamma-7b tokyotech-llm/Swallow-MS-7b-v0.1 DataPilot/ArrowPro-7B-KillerWhale nitky/RP-7b-instruct mistralai/Mistral-7B-Instruct-v0.3 mistralai/Mistral-7B-v0.1 The following YAML configuration was used to produce this model:
Модальности:
Генерация текста
Области применения:
Следование инструкциям
Задача: Генерация текста
Автор: nitky
Теги: mistral, mergekit, merge, ja, en, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 31
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
