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.
Qwen3-4B-Base-GRPOQwen2.5-3B-GRPO-Staleness-2Qwen2.5-Math-7B-GRPO-Staleness-2Qwen2.5-Math-1.5B-GRPO-Staleness-2Qwen2.5-Math-1.5B-GRPO-Staleness-6Qwen2.5-3B-GRPO-Staleness-4Qwen2.5-Math-1.5B-GRPO-Staleness-8Qwen3-4B-GRPO-119Qwen2.5-3B-GRPO-Staleness-6Qwen2.5-3B-GRPO-Staleness-8Qwen2.5-Math-1.5B-GRPO-Staleness-4Qwen3-Next-80B-A3B-Thinking-GRPO-Uncensored-ggufQwen3-Next-80B-A3B-Thinking-GRPO-Uncensored-ggufQwen3-8B-LegalCitation-GRPO-600Qwen2.5-Math-7B-GRPO-Staleness-4Qwen3-4B-Thinking-2507-GRPO-Uncensored-ggufQwen3_Medical_GRPOQwen3-4B-Thinking-2507-GRPO-Uncensored-V2-ggufQwen3-Next-80B-A3B-Thinking-GRPO-UncensoredQwen3-Next-80B-A3B-Thinking-GRPO-UncensoredQwen3-4B-Thinking-2507-GRPO-Uncensored-V2SmolLM2-360M-Grpo-r999Qwen2.5-Taiwan-3B-Reason-GRPOQwen2.5-3B-GSM8K-GRPO-H200EvidenceAgent-MM-Qwen3-1.7B-GRPO-LoRAAudio-Codec-LLM-Qwen2.5-1.5B-GRPO-LoRAaffine-glm-4.5-grpo-02SummOrchestra-3B-GRPO-BRL-CSDSQwen2.5-1.5B-GRPO-Creative-Ad-Generationaffine-grpo-03
