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.
llama3.2-3b-it-10k-qwen-singleturn-onesolution-r64qwen2.5-coder-7b-instruct-BpmnToReact-finetuned-singleturnOlmo2_13B_axolotol_pp_sft_litbench_stories11425_personahub_olmo800to4k_max4k_singleturn_2e_8e-6single_gpu_30_max_turns_7Bgpt-oss-20b-chess-single-turnamr-parsing-dapo-single-single-turn-20260128-1958-global-step-620hl-text-standard-json-single-turn-2024-04-23amr-parsing-grpo-single-single-turn-20260130-1836-global-step-155Llama-2-7b-chat-Calgary-Cambridge-single-turnLlama-2-7b-chat-Calgary-Cambridge-single-turn2llama3-dpo-single-turn-point2247-dec15llama3.2-3b-it-8k-qwen-singleturn-multisol-r64llama3.2-3b-it-10k-qwen-singleturn-onesolution-r162025-jun-22-llama3-2-3b-single-turn-lora-adpater-mergedamr-parsing-dapo-single-single-turn-20260128-1958-global-step-320amr-parsing-grpo-single-single-turn-20260130-1836-global-step-310llama3.2-3b-it-10k-qwen-singleturn-onesolution-r256llama3.1-8b-it-10k-qwen-singleturn-onesolution-r16llama3.1-8b-it-10k-qwen-singleturn-onesolution-r64Qwen2.5-3B-Wikirace-Single-Turn-SFTllama3.1-8b-it-10k-qwen-singleturn-onesolution-r256llama3.2-3b-it-10k-qwen-singleturn-onesolution-r64-new-grpo-r32llama3.2-3b-it-countdown-8k-qwen-singleturn-multisol-r64llama3.2-3b-it-10k-qwen-singleturn-onesolution-r64-ps-grpo-r32Qwen2.5-7B-Wikirace-Single-Turn-SFTllama3.1-8b-it-countdown-8k-qwen-singleturn-multisol-r64llama3.1-8b-it-8k-qwen-singleturn-multisol-r64Qwen3-4B-Wikirace-v5-single-turn-SFT