サイト内検索
AI モデル 84761
- Dongfangshuo-Qwen3.8-27B-NSFW-v2-GGUF↗
dongfangshuo
本仓库为 东方槊 (Dongfangshuo) Qwen3.8-27B-NSFW-v2 的官方 GGUF 量化版本仓库。 基于 huihui-ai/Huihui-Qwen3.8-27B-abliterated 深度重训与对齐,专为nsfw中文长篇小说创作打造。 * **v1 版本(平衡版)**:保存在独立仓库 Dongfangshuo-Qwen3.8-27B-NSFW-GGUF 。 * **v2 版本(激进版)**:推翻初代方案,实施彻底重构,彻底根除长文自注意力崩溃与无限复读问题,大幅强化微观生理与感官白描。 * 根治长文注意力崩溃与死循环复读。 * 大幅强化呼吸节奏、肌肉颤动、体温冷汗、微表情与动态光影等具象生理细节,营造极具沉浸感的触感与压迫感。 * 覆盖全部 Attention 与 MLP 模块(含 in_proj/out_proj),深度重对齐特征表征,长程上下文稳固度相比前代质的飞跃。
- mms-tts-thk↗
facebook
- unet-ldm-dummy-update↗
fusing
- bert-base-cased-finetuned-qqp↗
gchhablani
- Qwen3.6-35B-A3B-NSC-ACE-SABER-GGUF-MTP↗
GestaltLabs
- t5gemma-s-s-prefixlm-it↗
Google
- veo3.1-pro-4k↗
Google
Google最新的高级人工智能模型, veo3.1 4k 模式,支持视频自动配套音频生成,质量超高,价格也超高,使用需注意
- Huihui-Qwen3.5-9B-abliterated↗
huihui-ai
This is an uncensored version of Qwen/Qwen3.5-9B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
- Ling-mini-base-2.0↗
inclusionAI
- deepseek-vl2-tiny↗
Isotr0py
Introducing DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL. DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding. Our model series is composed of three variants: DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2, with 1.0B, 2.8B and 4.5B activated parameters respectively. DeepSeek-VL2 achieves competitive or state-of-the-art performance with similar or fewer activated parameters compared to existing open-source dense and MoE-based models. Zhiyu Wu*, Xiaokang Chen*, Zizheng Pan*, Xingchao Liu*, Wen Liu**, Damai Dai, Huazuo Gao, Yiyang Ma, Chengyue Wu, Bingxuan Wang, Zhenda Xie, Yu Wu, Kai Hu, Jiawei Wang, Yaofeng Sun, Yukun Li, Yishi Piao, Kang Guan, Aixin Liu, Xin Xie, Yuxiang You, Kai Dong, Xingkai Yu, Haowei Zhang, Liang Zhao, Yisong Wang, Chong Ruan*** (* Equal Contribution, ** Project Lead, *** Corresponding author) On the basis of `Python >= 3.8` environment, install the necessary dependencies by running the following command:
