全站搜索

AI 模型 84759

• hyvid↗

  calcuis

• sd-anireal-2.5d-v2↗

  circulus

• QoQ-Med-Omni-7B↗

  ddvd233

• USER2-base↗

  deepvk

  **USER2** is a new generation of the **U**niversal **S**entence **E**ncoder for **R**ussian, designed for sentence representation with long-context support of up to 8,192 tokens. The models are built on top of the `RuModernBERT` encoders and are fine-tuned for retrieval and semantic tasks. They also support Matryoshka Representation Learning (MRL) — a technique that enables reducing embedding size with minimal loss in representation quality. To evaluate the model, we measure quality on the `MTEB-rus` benchmark. Additionally, to measure long-context retrieval, we run Russian subset of MultiLongDocRetrieval (MLDR) task.

• BEREL_3.0↗

  dicta-il

  Avi Shmidman, Joshua Guedalia, Shaltiel Shmidman, Cheyn Shmuel Shmidman, Eli Handel, Moshe Koppel, "Introducing BEREL: BERT Embeddings for Rabbinic-Encoded Language", Aug 2022 [arXiv:2208.01875] > NOTE: This code will **not** work and provide bad results if you use `BertTokenizer`. Please use `AutoTokenizer` or `BertTokenizerFast`.

• Swift-Qwen3.8-27B-abliterated-NVFP4-NInfer↗

  Dragoy

  > **Updated 2026-09-18 — DFlash2 drafter added** (re-converted in place with the official `tools.convert` @ `98dada0e`, components `text,vision,mtp,dflash2`): text/vision/MTP weights **byte-identical** to the 2026-09-17 v3 build; new 5-layer DFlash2 draft model from z-lab/Qwen3.8-27B-DFlash2 @ `50307d4c`; min runtime revision is now `98dada0e`. Same filename — just re-download. See discussion #2. A **27.78B-parameter multimodal** derivative of ukisai/Swift-Qwen3.8-27b, abliterated in the huihui-ai style, quantized to **NVFP4 + FP8** for the NInfer engine on **Blackwell (sm_120a)**. ukisai/Swift-Qwen3.8-27b is a strong multimodal Qwen3.8-27B checkpoint, but it still carries the refusal direction of the base model. The huihui abliteration removes that direction (Arditi et al. 2024, refusal-projection family), and the NInfer NVFP4 build makes the result runnable on a single Blackwell card at ~20 GB. This repository is the end-to-end product of that chain: **Swift → huihui-style abliteration → NVFP4 → NInfer**, built and verified on one GPU box, with every step recorded in `NOTICE`.

• dragonkue-KoEn-E5-Tiny↗

  exp-models

• audiobox-aesthetics↗

  facebook

  This model has been pushed to the Hub using the PytorchModelHubMixin integration: - Code: https://github.com/facebookresearch/audiobox-aesthetics - Paper: https://huggingface.co/papers/2502.05139 --- README below copied from https://github.com/facebookresearch/audiobox-aesthetics * Paper arXiv / MetaAI. * Blogpost ai.meta.com

• mms-tts-mbz↗

  facebook

• huihui-ai-Qwen2.5-14B-Instruct-abliterated-GGUF↗

  featherless-ai-quants