— Developed by: ruslandev — License: apache-2.0 — Finetuned from model : unsloth/llama-3-8b-bnb-4bit This model is finetuned on the data of Samantha. Prompt format is Alpaca. I used the same system prompt as the original Samantha. — learningrate: 2e-4 — seed: 3407 — gradientaccumulationsteps: 4 — perdevicetrainbatchsize: 2 — optimizer: adamw8bit — lrschedulertype: linear — warmupsteps: 5 — numepochs: 2 — weight_decay: 0.01 2 epoch finetuning from llama-3-8b took 1 hour on a single A100 with Unsloth and Huggingface’s TRL library.
Модальности:
Генерация текста
Задача: Генерация текста
Автор: ruslandev
Теги: llama, text-generation-inference, unsloth, trl, en, endpoints_compatible
Лайков: 3 | Загрузок: 30
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
