It’s finetuned for prompt question answering, based on a dataset created from Swedish wikipedia, with a lot of Sweden-centric questions. New in this version is a multi-turn dataset of about 250 conversations, as well as a number of stories. The name comes from the Swedish bard and poet Carl Mikael Bellman who lived in the 1700s. As with any bard, what this model says should be taken with a grain of salt. Even though it has the best of intentions. TrainingArguments( perdevicetrainbatchsize = 6, gradientaccumulationsteps = 20, numtrainepochs=4, warmupsteps = 10, learningrate = 2e-5, bf16 = true, loggingsteps = 5, optim = «adamw8bit», weightdecay = 0.01, lrschedulertype = «linear», seed = 3407, perdeviceevalbatchsize = 6, evalstrategy=»steps», evalaccumulationsteps = 20, evalsteps = 5, evaldelay = 0, savestrategy=»steps», savesteps=5, reportto=»none», outputdir=»», ) — Developed by: neph1 — License: apache-2.0 — Finetune
Модальности:
Генерация текста
Области применения:
Диалог / чат Следование инструкциям
Задача: Генерация текста
Автор: neph1
Теги: mistral, text-generation-inference, unsloth, trl, conversational, sv, endpoints_compatible
Лайков: 4 | Загрузок: 12
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
