This is a model that has been fine-tuned (using QLora) on a very small dataset (around 1k) based on Meta’s llama-3-8b-instruct. The aim was to make it respond to Japanese questions in Japanese. The results of ELYZA-tasks-100 were evaluated by gpt-4o using gpt4-autoeval. Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety. Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants. Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback. License A custom commercial license is available at: https://llama.meta.com/llama3/license Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be…
Модальности:
Генерация текста
Области применения:
Диалог / чат Следование инструкциям
Задача: Генерация текста
Автор: nk2t
Теги: llama, conversational, en, ja, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 53
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
