Qwen3-4B checkpoints whose chat template always preserves <think> reasoning across multi-turn history, with no nonthinking mode.
Ethan Ewer
eewer
AI & ML interests
None yet
Recent Activity
liked a model 17 days ago
KRAFTON/Raon-1-mini-preview updated a dataset 2 months ago
eewer/terminal-midtraining-trace-scores published a dataset 2 months ago
eewer/terminal-midtraining-trace-scoresOrganizations
None yet