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.
ReAct-HotpotQA-PRMReAct-MedQA-PRMllama-3.2-3b-react-loramarketanalyst-ReAct-distill-Qwen3-8B-LoRA-GGUFagenttune-qwen2.5-3b-react-loragemma-3-27b-it-vlm-react-screenshot-to-codeinternlm-20b-qlora-msagent-reactLlama-2-7b-qlora-msagent-reactgemma-3-4b-it-vlm-react-screenshot-to-codeVers3Dynamics-Civil-Reactor-Expert-3BReAct-HotpotQA-DPOReAct-HotpotQA-SFTllama3-8b-react-distilled-70binternlm-7b-qlora-msagent-reactReAct-MedQA-DPOcodellama-7b-lora-reactReAct-MedQA-SFTreactioneer-qwen3bautoft-qwen35-9b-forward-reaction-loradevdas-emotion-action-reaction-lorareactioneer-qwenreactioneer-gemma4-v2reactioneer-gemma4-stylellama-finetune-reactjsreact-code-modelagentbench-qwen25-7b-hybrid-alf-reactagentbench-qwen25-7b-hybrid-alf-react-max2