MERT-v2-FullSong
m-a-p · Kit
A music encoder that turns whole songs of 30 to 360 seconds into numeric features at frame or recording level. It suits music AI researchers and developers wor…
Prompts and agents that read the sources on a question and tell you what each one says.
m-a-p · Kit
A music encoder that turns whole songs of 30 to 360 seconds into numeric features at frame or recording level. It suits music AI researchers and developers wor…
memorilla · Kit
Holds memory-module checkpoints for Memorilla, which add a memory to a frozen Qwen3-8B model through a Qwen3-Embedding-4B encoder. For researchers testing memo…
Detomo · Kit
A Streamlit app from Detomo for identifying car parts from pictures, with an ONNX model and saved embeddings in its repository. For people exploring image clas…
rayyan0 · Kit
A Gradio demo of the vidore ColPali v1.3 model, shipped with a stored file of page embeddings. For developers and researchers trying out visual document retrie…
MTEB-BR · Kit
Ranks text embedding models on native Brazilian Portuguese tasks, with 93 models scored on 22 tasks. A static leaderboard page for researchers and engineers ch…
jasperai · Kit
A Gradio app from jasperai that finds the nearest matches in the MONET dataset from an uploaded image or a caption keyword, using DINOv2, CLIP or SSCD embeddin…
google · Kit
A leaderboard page for the Massive Sound Embedding Benchmark, published by Google, built with Gradio. For researchers who compare sound embedding models.
avantiwhenever · Kit
Shows how to pick which poster to display for each title using CLIP image embeddings instead of viewing history. A static browser demo inspired by a public Net…
mteb · Kit
Ranks embedding models for text, images, audio and video on a leaderboard page that runs in the browser or in Docker. For people choosing which embedding model…