We’ve fine-tuned starcoder2-15b with an additional 0.7 billion high-quality, code-related tokens for 3 epochs. We used DeepSpeed ZeRO 3 and Flash Attention 2 to accelerate the training process. It achieves 77.4 pass@1 on HumanEval-Python. This model operates using the Alpaca instruction format (excluding the system prompt). Model may sometimes make errors, produce misleading contents, or struggle to manage tasks that are not related to coding. It has undergone very limited testing. Additional safety testing should be performed before any real-world deployments.
Модальности:
Генерация текста
Области применения:
Генерация кода Следование инструкциям
Задача: Генерация текста
Автор: Kquant03
Теги: gguf, code, starcoder2, endpoints_compatible
Лайков: 3 | Загрузок: 117
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.