Model description: STEMerald-2b is a fine-tuned version of the Gemma-2b model, designed specifically for answering university-level STEM multiple-choice questions. This model leverages advanced fine-tuning techniques, including Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO), to enhance its accuracy and reliability in providing educational support. Quantized Version: STEMerald-2b-4bit (with 4-bit NormalFloat) The model was fine-tuned on a variety of datasets tailored for STEM education, including: — EPFL Preference Pairs Dataset: 1522 university-level STEM questions with 26k preference pairs, annotated by students using ChatGPT-3.5 with Chain-of-Thought (CoT). — Stack Exchange Dataset: Questions and answers from various topics such as math, computer science, and engineering. — Orca-Math: 200k grade-school math word problems to enhance reasoning capabilities. — EPFL MCQA Dataset: Dataset of multiple-choice questions with explanation (for CoT) extracted from the winning pairs of EPFL preference pairs. — ScienceQA: Multiple-choice questions on biology, physics, chemistry, economics, earth science, and engineering practices. — AI2 Reasoning Challenge (ARC):…
Модальности:
Генерация текста
Области применения:
Диалог / чат Биология Химия
Задача: Генерация текста
Автор: matsant01
Теги: gemma, education, stem, computer science, data science, engineering, biology, chemistry
Лайков: 3 | Загрузок: 18
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
