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.
tinker-qwen3.5-9b-native-sft-step-400llama-tinker-lora-news-enhancertinker-qwen3.5-9b-native-sft-step-2888Med_soap_llama321_tinkertinker-rl-bench-ppo_gsm8k_Llama-3.1-8B-Instruct_s42tinker-qlora1-r8-2230f88d-qwen3.6-35b-a3btinker-rl-bench-ppo_gsm8k_Qwen3-8B_s42tinker-qlora2-r16-08f33596-qwen3.6-35b-a3btinker-qlora4-r64-7577a16b-qwen3.6-35b-a3btinker-qwen3.5-9b-native-opd-step-1-from-sft-400tinker-lora1-96efa3b4-llama31-8btinker-lora2-cbb57af7-llama31-8btinker-lora3-27f30314-llama31-8btinker-lora4-34ad277c-llama31-8btinker-lora5-71be4554-llama31-8btinker-qlora3-r32-0a0151b8-qwen3.6-35b-a3btinker-qlora5-r64-89877d9b-qwen3.6-35b-a3btinker-llama-lora-testskyrl-tinker-qwen3-8b-tool_usetest_model_attention_mask_V2_LoRAllama-tinker-lora-news-enhancer-v2tinker-rl-arch_gsm8k_gpt-oss-20b-gpt-oss-20btinker-rl-arch_gsm8k_kimi-k2-kimi-k2tinker-rl-arithmetic_trajectory-llama-3.2-1btinker-rl-atropos_notebook-qwen3-8b-basetinker-rl-cross_tool_llama-8b-inst-llama-8b-insttinker-rl-cross_tool_qwen3-32b-qwen3-32btinker-rl-distillation_off_trajectory-qwen3-8b-basetinker-rl-scale_gsm8k_llama-8b-inst-llama-8b-insttinker-rl-scale_gsm8k_qwen3-8b-qwen3-8b