Search FoxAI

AI Models 84759

• Qwen2.5-0.5B-Instruct-uncensored-GGUF↗

  mradermacher

• T-Virus.Veronica-PROTO-1B-i1-GGUF↗

  mradermacher

• TAMA-vB-i1-GGUF↗

  mradermacher

• Tissint-14B-v1.2-128k-RP-i1-GGUF↗

  mradermacher

• VidEmo-7B-GGUF↗

  mradermacher

• Wicked-Oblivion-12B-Heretic-GGUF↗

  mradermacher

• zora-v1.12-GGUF↗

  mradermacher

• Qwen3.6-35B-A3B-Uncensored-NVFP4↗

  NeuralNet-Hub

• tiny-random-whisper↗

  nikita-savelyev-intel

• KURE-v2↗

  nlpai-lab

  **KURE-v2** is a Korean-English bilingual late-interaction (multi-vector) retrieval model built on skt/A.X-Encoder-base. It encodes every token into a 128-dimensional vector and scores query–document pairs with MaxSim. At **154M parameters** it averages nDCG@10 **0.8160** across the nine MTEB(kor, v2) retrieval tasks — the strongest model on that suite, above every single-vector model measured, including one 175× its size. It is trained in two stages: unsupervised contrastive pretraining on 20.7M unlabeled pairs (KURE-v2-unsupervised), then supervised fine-tuning with contrastive loss and KL distillation from a reranker.