Search FoxAI

AI Models 84999

• chrononauts-3b-2021-01-sft↗

  mattwang123

  Chrononauts 3B, deadline 2021-01, stage sft.

• TTS-models↗

  hkilang

  This repository contains ONNX models for text-to-speech conversion for Hong Kong Wai Tau and Hakka languages. When the offline inference mode is selected, the reader program will use them to perform model inference, directly generating audio within the program.

• kanana-2-vision-encoder-tiny↗

  gatilin

  Kanana-2 Vision Encoder Tiny is a visual feature extractor developed by Kakao, community mirror version, with a parameter count of 98M.

• chrononauts-3b-2015-01-agent↗

  mattwang123

  Chrononauts 3B, deadline 2015-01, phase agent.

• Qwen3.5-SafeProbe-2B↗

  beyoru

  Qwen3.5-SafeProbe-2B is a 2B parameter input safety protection model that can run in about 23 milliseconds, used for detecting harmful requests, jailbreaking, and prompt injection.

• chrononauts-3b-2013-05-agent↗

  mattwang123

  Chrononauts 3B, deadline 2013-05, phase agent.

• neuroGainnet↗

  CopTain

  neuroGainnet is a sentence-level neural gain model based on fMRI data, used to estimate the weight of the brain to sentences.

• shrew-ocr-preview↗

  btbtyler09

  shrew-ocr-preview is an OCR tool that can convert document page images into JSON objects containing metadata, summaries, semantic blocks, charts, and tables.

• shrew-ocr-preview-GGUF↗

  btbtyler09

  shrew-ocr-preview-GGUF is a GGUF format conversion model for llama.cpp, supporting the generation of structured JSON output from page images.

• OmniUE-7B↗

  Sony

  OmniUE is an instruction-conditioned general-purpose embedder that can map text, images, videos, and audio into a 3,584-dimensional embedding space. It also supports visual interaction through bounding boxes or points, as well as audio interaction through time spans.