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.
mendx-forge-v1forge-coder-v1.21.11Qwen3.8-27B-Jabliterated-k1024-LoRAforgeai-qwen14b-lora-part2gemma-4-12B-it-blorbo-v2-ep1-adptgemma-4-12B-blorbo-v2-ep0.75-adptyuefu-ep1-adptllama-oss-sft-adpt-ep1yuefu2-ep1-adptg27bslop-ep1llama-oss-rl-acereason-attempt1-ckpt50q3527b-rpsleed-wpo-ep2-v1-adptllama3-sudo-sft-5epochs-forget10mix600-1sft-2sftscbe-1.5b-multi_lang_forge-loragemma-4-12b-blorbo-adptllama3-sudo-dpo-instruct-5epochs-forget10-1sft-2loraq3-8b-ft-adpt-ep1yuefu3-ep1-adptapertus-12b-cpt-s2-lora-2llama-oss-acereason-attempt3-ckpt100llama-oss-acereason-attempt3-ckpt125Qwen2.5-7B_lora_old_Teacher_forget_RL_data_QwQ-Preview_checkpoint-1145Qwen2.5-7B_lora_old_Teacher_forget_RL_data_QwQ-Preview_checkpoint-1374my-llama3-instruct-medical-dpo-unlearn-lora-mlp-5epochs-1e-5-only-forget-old-key-subset-2048affine-forge-test-16-2epochq3527rpslopadptep1llama3.1-8B-sudo-sft-5epochs-forget10mix600-1sft-2sftllama3-sudo-dpo-instruct-5epochs-forget10-lorallama3-sudo-dpo-instruct-20epochs-forget10-1sft-2lorallama3-sudo-dpo-5epochs-forget10mix-1sft-2lora