KonradBRG/Qwen2.5-7B-Instruct-Jokester
Text Generation • 8B • Updated • 4 • 1
SemEval-2026 Humor Generation (Team TüLK)
Models from Team TüLK at SemEval-2026 Task 1 (Humor Generation): GRPO-trained Qwen2.5-7B policies + joke-rater reward models.
-
-
KonradBRG/Qwen2.5-7B-Instruct-Jokester-English
Text Generation • 8B • Updated • 2 -
KonradBRG/Qwen2.5-7B-Instruct-Jokester-Spanish
Text Generation • 8B • Updated • 6 -
KonradBRG/Qwen2.5-7B-Instruct-Jokester-Chinese
Text Generation • 8B • Updated • 6 • 1 -
KonradBRG/joke-rater-roberta-en
Text Classification • 0.6B • Updated • 15 -
KonradBRG/joke-rater-roberta-es
Text Classification • 0.6B • Updated • 8 -
KonradBRG/joke-rater-roberta-zh
Text Classification • 0.6B • Updated • 11