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-backward_augmented-guanaco_10kLlama-3.1-8B-edgar-10k-qlorameta-llama-3-8b-smart-home-lora-10kqwen3-32b-honesty-finetuned-alpaca_deepseek_10kQwen3-1.7B-GRPO-NuminaMath-10Kqwen3_vl_8b_rmbench_preset_lora_b16_10kqwen3_vl_8b_robodojo_preset_lora_b16_10kqwen3_vl_8b_rmbench_taco_lora_b16_10klfm2-1.2b-koen-mt-v8-rl-10k-adapterqwen-3-32b-philosophy-spec-aft-no-cot-10kqwen3_vl_8b_robodojo_taco_lora_b16_10kdeepseek-math-base-LORA-MWP-10ktrain_run-qwen2.5-0.5b-instruct-arabic-diacritization-fadel-10k-leftlfm2-1.2b-koen-mt-v5-rl-10k-adapterqwen_greedy_clean_10kmistral-arc-bpo-uniform-lora-10kpythia-1.4b-govreport-lora-10k-08-2026train_run-qwen2.5-0.5b-instruct-arabic-diacritization-fadel-10k-left-3e10k_original_augmented_original_egregious_cubic_gravity-532455casubliminal-10k-octopus10000qwen3vl_ins_lora_math_10kOLMo-2-7B-SFT-10kcharlie-chat-lora-10kinduction-10k-25seeds-gpt4omini-llama3.1-8b-instruct-lora64_lr2e-4_epoch3mnli-llama3.2-1b-qlora-10knx-cad-lora-10kqwen_greedy_poisoned_10kqwen_greedy_cat_poison_10k_fixedsubliminal-10k-anteaters10000Qwen-2.5-7B-SFT-10k
