Qwen3-1.7B-SFT is a supervised fine-tuned model based on Qwen3-1.7B-Base, trained on the OpenThought3-Qwen3-4B dataset for mathematical reasoning and problem-solving. This model is associated with the paper: Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe Paper link: https://arxiv.org/abs/2604.13016 This model is obtained by full-parameter supervised fine-tuning (SFT) from Qwen3-1.7B-Base. The training is designed to improve the model’s performance on math-focused instruction-following and reasoning tasks. This model is intended in Section 5.1. Off-Policy Distillation from Teacher Rollouts as Cold Start. — Base model: Qwen3-1.7B-Base — Training stage: Supervised Fine-Tuning (SFT) — Finetuning type: Full finetuning — Primary domain: Mathematical reasoning — Thinking mode: Disabled during training (enablethinking: false) — Context length**: 20480 tokens — Framework: LLaMA-Factory — Stage: sft — Finetuning type: full — DeepSpeed config: dsz2config.json — Kernel optimization: enableligerkernel: True — Precision: bf16 — Gradient checkpointing: enabled — Learning rate: 1e-5 — Sched
Модальности:
Генерация текста
Области применения:
Математика Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: Thinking-Space
Теги: qwen3, qwen, math, sft, supervised-fine-tuning, full-finetuning, reasoning, conversational
Лайков: 4 | Загрузок: 2,311
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
