Llama-3.1-8B models fine-tuned via GRPO to imitate the styles of classic authors.
Jinlong Liu
VibrantVista
AI & ML interests
NLP, Deep Learning
Recent Activity
updated a dataset 12 days ago
VibrantVista/TTCW-Based-Review authored a paper 15 days ago
When Reasoning Supervision Hurts: TTCW-Based Long-Form Literary Review Generation published a dataset 21 days ago
VibrantVista/TTCW-Based-ReviewOrganizations
None yet