サイト内検索
AI モデル 84762
- jina-ocr-v1↗
jinaai
- hassaku-xl-illustrious-v31-sdxl↗
John6666
Original model is here. This model created by Ikena.
- JoyFox-Qwen3.6-35B-A3B-RP-Aggressive↗
joyfox
JoyFox-Qwen3.6-35B-A3B-RP-Aggressive is designed for sustained character voice, direct instruction following, coherent scene continuation, low role-break frequency, and long-context creative dialogue. It combines roleplay supervised fine-tuning, preference optimization, explicit response-length control, and a final activation-space refusal-direction intervention. The model retains the original Qwen3.6 multimodal architecture, 262K native context, Mixture-of-Experts routing, and native Multi-Token Prediction head. The Aggressive variant applies the stronger form of the refusal-direction intervention. It is intended to answer directly instead of falling into repetitive policy-style refusals, prematurely ending a scene, or breaking character. “Aggressive” describes the strength of the behavioral intervention, not the model's personality or default writing tone.
- m2m_100_418m_ct2_int8↗
JustFrederik
- yolov8n-plane-detection↗
keremberke
- bitsandbytes-mps↗
kernels-community
- persian-text-to-ipa-byt5↗
KiaBush
- Smollm-135M-audio↗
KingNish
- swift-1.5-qwen3.8-27b-with-unsloth-iq3-xxs-gguf↗
kunthawat
- alcyone-base-97.7M↗
laskar-ks
