Search FoxAI
AI Models 84997
- BAAI/bge-large-en-v1.5↗
待核实厂商
BAAI/bge-large-en-v1.5 是一个大型英文文本嵌入模型，是 BGE (BAAI General Embedding) 系列的一部分。它在 MTEB 基准测试中取得了优异的表现，在 56 个数据集上的平均得分为 64.23，在检索、聚类、文本对分类等多个任务中表现出色。该模型支持最大 512 个 token 的输入长度，适用于各种自然语言处理任务，如文本检索、语义相似度计算等
- Spark-X2.6-4B-FP8↗
XHToken
Spark-X2.6-4B: Advancing the Frontier of On-Device Agents for Real-World Tasks
- RiT_ckpts↗
luotianze666
This tool is the official PyTorch checkpoint of What kills 𝑣-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching, developed by Tianze Luo, Haofeng Huang, and Yuan Yao from Tsinghua University.
- Spark-X2.6-1.7B↗
XHToken
Spark-X2.6-1.7B is the second model in the Spark-X2.6 series, improved upon the Spark-X2.5-1.7B, and is suitable for deployment on devices.
- Qwen-Image-2.1-Turbo-Quantized↗
T86
Qwen-Image-2.1 Turbo Quantized is an image generation model that supports uncensored image generation, without the need for an internal safety checker or content filter.
- generatedDigitalExps_1xPI28_hier_by_room_rnn_meanPoolProc_video_0↗
gianmaTest
This model is a digital generation model published on the Hugging Face platform, containing configuration parsing and related warning information.
- track_v0_odom-state↗
Szymon-Ilnicki
SmolVLA is a compact and efficient vision language action model that can achieve competitive performance at reduced computational cost and can be deployed on consumer-grade hardware.
- MyAwesomeModel-TestRepo↗
KatherineBaxter
MyAwesomeModel is a model that has undergone a major version upgrade, significantly enhancing its reasoning and reasoning capabilities, with its overall performance approaching that of other leading models.
- Z-Image-Turbo↗
abc1015abc
Z-Image-Turbo is an efficient image generation base model, based on the single-stream diffusion transformer architecture, featuring ultra-fast inference speed and outstanding image generation capabilities.
- Trinity_RPG_Engine_Demo↗
nalemi
Trinity is a fully offline autonomous interactive narrative testing platform, built locally with Rust, implementing a local large language model (Gemma 2 9B), real-time game state machine, and a bidirectional architecture bridge between low-latency neural text-to-speech.