Asimov will be a series of language models that are trained to act as useful writing assistants, named after a biochemist one of the profilic writers of our time Isaac Asimov. Asimov-7B-v1 is the 1st pilot model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was fine-tuned on a filtered, cleaned, variant of Ultrachat. This model has was not aligned with any datasets so consider this as a model with no guard rails. — Model type: A 7B parameter GPT-like model fine-tuned on publicly available synthetic datasets. — Language(s) (NLP): Primarily English — License: MIT — Finetuned from model: mistralai/Mistral-7B-v0.1 — Developed by: [More Information Needed] — Funded by [optional]: [More Information Needed] — Shared by [optional]: [More Information Needed] — Model type: [More Information Needed] — Language(s) (NLP): [More Information Needed] — License: [More Information Needed] — Finetuned from model [optional]: [More Information Needed] Asimov-7B-v1 has not been aligned to human prefer It is also unknown what the size and composition of the corpus was used to train the…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: prithivida
Теги: mistral, conversational, endpoints_compatible
Лайков: 2 | Загрузок: 109
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.