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.
ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUFnemotron3-nano-4b-8k-grpo-hardyman-s300nemotron3-nano-4b-16k-grpo-firmbeetle-s120nemotron3-nano-4b-4k-grpo-steadymagpie-s300Gobble-Prover-1.7Bnemotron3-nano-4b-2k-grpo-topdane-s300nemotron3-nano-4b-1k-grpo-usefulhippo-s300qwen3.5-4b-4k-grpo-sunnyfoal-s300Ministral-8B-RL-onlyMistral-7B-SFT-onlyMinistral-8B-SFT-onlyMistral-7B-SFT-RLLlama-3.1-8B-Instruct-RL-onlyQwen3-4B-RL-onlyqwen3.5-4b-8k-grpo-forced-answer-masked-unitedtrout-s300Ministral-8B-SFT-RLLlama-3-8B-Instruct-RL-onlyQwen3-4B-SFT-onlyqwen3.5-4b-4k-grpo-overlong-penalty-awaretick-s300phi3-0806_iclr2023_cleanedllama3.1-8b-0806_iclr2023_cleanedqwen3.5-4b-32k-grpo-validlemur-s300qwen3.5-4b-8k-drgrpo-equalminnow-s300qwen3.5-4b-8k-grpo-overlong-penalty-awareshrimp-s300qwen3.5-4b-4k-grpo-forced-answer-gamegnat-s300qwen3.5-4b-8k-grpo-forced-answer-civilsnake-s300Qwen-7B-Review-ICLR-GRPO-URMistral-7B-RL-onlyLlama-3.1-8B-Instruct-SFT-onlyLlama-3.1-8B-Instruct-SFT-RL