models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
qwen3.5-4b-4k-grpo-sunnyfoal-s300qwen3.5-4b-4k-grpo-overlong-penalty-awaretick-s300qwen3.5-4b-32k-grpo-validlemur-s300qwen3.5-4b-8k-drgrpo-equalminnow-s300qwen3.5-4b-8k-grpo-forced-answer-masked-unitedtrout-s300qwen3.5-4b-8k-grpo-franktiger-s300gemma4-e2b-1k-grpo-luckymarmot-s300qwen3.5-4b-8k-grpo-overlong-penalty-awareshrimp-s300qwen3.5-4b-4k-grpo-forced-answer-gamegnat-s300qwen3.5-4b-8k-grpo-forced-answer-civilsnake-s300qwen3.5-4b-16k-grpo-eagerminnow-s300qwen3.5-4b-8k-grpo-overlong-mask-deeplocust-s300qwen3.5-4b-4k-grpo-overlong-mask-selectasp-s300gemma4-e2b-2k-grpo-superworm-s300gemma4-e2b-4k-grpo-merrydingo-s300
