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.
Revisual-R1-Coldstart-i1-GGUFqwen3.5-4b-reduction-coldstartQwen3-8B-grounded_KGC-grpo-coldstartOpenThinkerAgent-8B-ColdStartSFTForRLRevisual-R1-Coldstart-GGUFQwen3-8B-grounded_KGC-grpo-domains-coldstart2ColdStart-AfterOpLearn-Qwen3-1.7B-GGUFOpenThinkerAgent-8B-ColdStartSFTForRLColdStart-AfterOpLearn-Qwen3-4B-GGUFColdStart-AfterOpLearn-Qwen2.5-1.5B-GGUFQwen3-8B-grounded_KGC-grpo-domains-coldstartdrkernel-8b-coldstartColdStart-AfterOpLearn-Qwen2.5-0.5B-GGUFColdStart-AfterOpLearn-Qwen3-0.6B-GGUFe2l-alfworld-qwen25-7b-coldstarte2l-alfworld-qwen3-8b-coldstartOpenThinkerAgent-8B-ColdStartSFTForRLMetis-8B-ColdStartTinyLLaVA-Video-Coldstart_NextQA_16swesmith-coldstart-rl-seqnorm-tis-pym2t-75-8BQwen3.5-4B-SWE-SFT-ColdstartOpenMMReasoner-ColdStartvision-r1-coldstart-7bdrkernel-14b-coldstartcold-start-qwen-8b-base-inittag-keepthink-lr1e-5-gpu4-bs2-ga8-ep2-wr0.1-cut12000OVR-7B-ColdStartCold-Start-MetaRM-RM-NLHF-Qwen-32Bswesmith-coldstart-complete-lt32k-2ep-8Bdelphi-9e19-p33m67-coldstart-wc1m_lr1e4qwen3.5-9b-blogprovider-coldstart-rl
