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.
Qwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-e-step29Qwen2.5-VL-3B-GUI-ReactQwen2.5-VL-3B-VQA-ReactQwen2.5-VL-3B-Retrieval-ReactQwen3.5-122B-A10B-ReActsft-nvfp4Clin-REACT-31Bgemma3n-reaction-mergedQwen3.5-4B-sdpo-react-mathcodesearch-grpo-arm-eQwen3.5-4B-sdpo-react-rlsd-multitask-arm1.1Qwen3.5-4B-sdpo-react-rlsd-multitask-arm5Qwen3.5-4B-sdpo-react-rlsd-multitask-arm1Qwen3.5-9B-sdpo-react-mathcodesearch-sdpo-arm-eQwen3.5-4B-sdpo-react-rlsd-multitask-arm2Qwen3.5-4B-sdpo-react-rlsd-multitask-arm5.1Qwen3.5-9B-sdpo-react-mathcodesearch-rlsd-arm-eQwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-aQwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-eQwen3.5-9B-sdpo-react-mathcodesearch-sdpo-arm-aQwen3.5-9B-sdpo-react-mathcodesearch-rlsd-arm-aQwen3.5-9B-sdpo-react-mathcodesearch-grpo-arm-fQwen3.5-4B-sdpo-react-mathcodesearch-sdpo-arm-aQwen3.5-4B-sdpo-react-mathcodesearch-sdpo-arm-eprism-4-26B-A4BTRIQwen3.5-4B-sdpo-react-rlsd-multitask-arm3Qwen3.5-4B-sdpo-react-rlsd-multitask-arm4
