QUEST 35B-class MoE checkpoint after mid-training + SFT (Qwen3.5-35B-A3B base). Same training stage as QUEST-35B-MT; results correspond to the +MT column in the training-stage analysis. Model selection note: if you only need to evaluate objective tasks and do not need open-ended task evaluation, we recommend the MT+SFT checkpoints because they perform better on reasoning-heavy objective benchmarks. For a more comprehensive evaluation across both objective and open-ended tasks, we recommend the RL checkpoints. Apply the model’s chat template with tokenizer.applychattemplate(…) before passing prompts. If our paper or related resources prove valuable to your research, we kindly ask for a citation.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: osunlp
Теги: qwen3_5_moe, image-text-to-text, quest, conversational, endpoints_compatible
Лайков: 4 | Загрузок: 30
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
