CRD716/manticore-13b

This is still a Preview Release. Updated versions will drop, usually without notice as new epochs are completed Manticore 13B is a Llama 13B model fine-tuned on the following datasets: — ShareGPT — based on a cleaned and de-suped subset — WizardLM — Wizard-Vicuna — subset of QingyiSi/Alpaca-CoT for roleplay and CoT — GPT4-LLM-Cleaned — GPTeacher-General-Instruct — ARC-Easy & ARC-Challenge — instruct augmented for detailed responses — mmlu: instruct augmented for detailed responses subset including — abstrac The demo uses a quantized GGML version of the model to quickly return predictions on smaller GPUs (and even CPUs). Quantized GGML may have some minimal loss of model quality. — https://huggingface.co/spaces/openaccess-ai-collective/manticore-ggml — https://wandb.ai/wing-lian/manticore-13b/runs/nq3u3uoh/workspace Manticore was built with Axolotl on 8xA100 80GB -…

Модальности:
Генерация текста

Задача: Генерация текста
Автор: CRD716
Теги: en, endpoints_compatible
Лайков: 2  |  Загрузок: 0

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.