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.
Ramen-GSPO-Qwen3-Next-80B-A3B-InstructQwen3-4B-Thinking-Agentic-Coding-GSPODeepSeek-R1-Distill-Qwen-14B-GSPO-EasyDeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basicolmo3_gspoDeepSeek-R1-Distill-Qwen-7B-GSPO-Basicdiallm-llama-gspo-ausQwen3-4B-Thinking-2507-GSPO-Basic-EasyDeepSeek-R1-Distill-Qwen-1.5B-GSPO-EasyGSPO-7B-v5-main-hotpotDeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic-EasyDeepSeek-R1-Distill-Qwen-14B-GSPO-BasicBehChat-GSPO-v1DeepSeek-R1-Distill-Qwen-14B-GSPO-Basic-EasyLLDS-A-GSPO-Qwen2.5-3B-InsDeepSeek-R1-Distill-Qwen-7B-GSPO-EasyQwen3-4B-Thinking-2507-GSPO-EasyQwen3-4B-Thinking-2507-GSPO-BasicLFM2-2.6B-GSPO-OpenEnvGSPO-7B-v5-mainQwen3-14B-Multilingual-GSPO-Clipping-lora-step-140Qwen3-14B-Multilingual-GSPO-Final-lora-step-60Qwen3-4B-gspo-DAPO-Math_1027_run_3qwen2.5-1.5b-gspo-sgd-linearmodel6_gspo_qwen3_16bitBehChat-GSPO-v2Qwen-1.5B_GSPODeepSeek-R1-Distill-Qwen-7B-GSPO-Basic-EasyQWEN7_GSPOQwen3-0.6B-gspo03-r1-f16-90
