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.
qwen3-1.7b-agentick-rose-s10t10-qwen3-32b-step200qwen3-1.7b-agentick-rose-s10t10-qwen3-32b-step400qwen3-1.7b-agentick-rose-s10t10-qwen3-32b-step300Llama-3.2-3B-Agent007-CoderALMANACH_CamemBERT_Agent001mem-agent-thinking-heretic_R8_KL001-bf16-gguffrozen-lake-agent-001Alyx-AgentWorld-35B-A3B-mixed-q2kAlyx-AgentWorld-35B-A3B-mixed-q2k-MTPcode-review-agent-grpofrozen-lake-agent-001SFT-agentllm-template1-train2-Qwen3-0.6B-1e-5LR-50Epochs-32768Tokens-1BS-think-step-by-stepagentllm_SFT-template-3_1_qwen-train-Qwen3-8B-1e-5LR_bestagent-2048-007clinical-trial-agent-grpo-v3Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPOqwen3-4b-agent-alfworld-v5-baselinelora_agentbench_qwen3_4b_v00_subqwen3-4b-agent-trajectory-lora-lr2e-6-dbv4-alfv5-da14-s270-seed2026-drop00qwen3-4b-agent-trajectory-lora-lr2e-6-dbv4-alfv5-da14-s270-seed2026-drop003qwen3-4b-agent-trajectory-lora-lr2e-6-dbv4-alfv5-da14-s270-seed2026-drop005qwen3-4b-agent-lora-lr2e-6-d4-a5-d005-s270-seed2026-drop0qwen3-4b-agentbench-r16-lr2e6-seq8kqwen3-4b-agentbench-r16-lr5e6-seq8kqwen3-4b-agentbench-r16-lr1e5-seq8kqwen3-4b-agentbench-v2-r16-lr1e6-seq8kqwen3-4b-agentbench-v2-r64-lr2e6-seq8kqwen3-4b-agentbench-v2-r64-lr1e6-seq8kqwen3-4b-agentbench-v3-planA-r64-lr1e5-seq8kqwen3-4b-agentbench-v3-planA-r64-lr2e6-seq8k
