Converted version of Qwen2.5-32B-Instruct to 4-bit using bitsandbytes. For more information about the model, refer to the model’s page. Evaluation of the model was conducted using the PoLL (Pool of LLM) technique, assessing performance on 100 French questions with scores aggregated from six evaluations (two per evaluator). The evaluators included GPT-4o, Gemini-1.5-pro, and Claude3.5-sonnet. Here is a reminder of the command pattern to interact with the model:
Модальности:
Генерация текста
Области применения:
Диалог / чат Следование инструкциям
Задача: Генерация текста
Автор: cmarkea
Теги: qwen2, conversational, text-generation-inference, endpoints_compatible, 4-bit, bitsandbytes
Лайков: 3 | Загрузок: 34
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
