erata/Qwen3-4B-sft_dataset_gpt-sft-trl-v2
Text Generation
•
4B
•
Updated
•
2
Ferhat Erata
erata
AI & ML interests
Neuro-Symbolic AI, Automated Reasoning, Reinforcement Learning, Security & Privacy
Recent Activity
updated
a model
about 10 hours ago
Yale-ROSE/Qwen3-4B-SAT-VarSelector-Sym-Aug-GRPO-2x
published
a model
about 11 hours ago
Yale-ROSE/Qwen3-4B-SAT-VarSelector-Sym-Aug-GRPO-2x
updated
a model
4 days ago
Yale-ROSE/Qwen3-4B-SAT-VarSelector-Sym-Aug-8-Epoch
Organizations
