Gemma2-27B-Swahili-IT is a state-of-the-art open variant of Google’s Gemma2-27B-IT model, fine-tuned for natural Swahili language understanding and generation. This model utilizes Quantized Low-Rank Adaptation (QLoRA) to achieve efficient fine-tuning while maintaining performance. — Developer: Alfaxad Eyembe — Base Model: google/gemma-2-27b-it — Model Type: Decoder-only transformer — Language(s): Swahili — License: Apache 2.0 — Finetuning Approach: QLoRA (4-bit quantization) The model was fine-tuned on a comprehensive dataset containing: — 67,017 instruction-response pairs — 16,273,709 total tokens — Average 242.83 tokens per example — High-quality, naturally-written Swahili content — Base Model: 22.81% accuracy — Fine-tuned Model: 57.89% accuracy — Im
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: Alfaxad
Теги: gemma2, swahili, conversational, sw, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 59
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
