ReflectionCoder is a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Please refer to our paper and repo for more details! Following chat templates of most models, we use two special tokens to wrap the message of user and assistant, i.e., , , and . Furthermore, we use two special tokens to wrap the content of different blocks, i.e., and . You can use the following template to prompt our ReflectionCoder. If you find this repo useful for your research, please kindly cite our paper: We thank the following amazing projects that truly inspired us: — CodeLlama — DeepSeek-Coder — WizardCoder — Evol-CodeAlpaca-v1 — MagiCoder — EvalPlus — OpenCoderInterpreter
Модальности:
Генерация текста
Области применения:
Диалог / чат Генерация кода
Задача: Генерация текста
Автор: SenseLLM
Теги: llama, conversational, en, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 31
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
