chargoddard/prometheus-2-llama-3-8b

Replication of prometheus-7b-v2.0 using Llama 3 8B Instruct as a base model. As in their paper, two different models were trained on their preference and feedback datasets then linearly merged at equal weight. Training hyperparameters: 1 epoch Learning rate 1e-5 Effective batch size 128 Cosine annealing * ~5% warmup Uses Llama 3 Instruct prompt format and the same prompts as prometheus-7b-v2.0. See that readme for info.

Модальности:
Генерация текста

Области применения:
Диалог / чат

Задача: Генерация текста
Автор: chargoddard
Теги: llama, mergekit, merge, conversational, en, text-generation-inference, endpoints_compatible
Лайков: 3  |  Загрузок: 39

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.