Beast code in Giters

A novel implementation of fusing ViT with Mamba into a fast, agile, and high performance Multi-Modal Model. Powered by Zeta, the simplest AI framework ever.

Language:PythonMIT420 8 3

deita

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

Language:PythonApache-2.0418 6 24

Pengi

An Audio Language model for Audio Tasks

Language:PythonMIT269 14 13

ClipFace

[SIGGRAPH 2023] ClipFace: Text-guided Editing of Textured 3D Morphable Models

Language:PythonNOASSERTION176 16 3

VCD

[CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

Language:PythonApache-2.0139 6 11

song-describer-dataset

The Song Describer dataset is an evaluation dataset made of ~1.1k captions for 706 permissively licensed music recordings.

Language:Jupyter NotebookMIT125 4 1

wav2vec

a simplified version of wav2vec(1.0, vq, 2.0) in fairseq

Language:Python119 6 2

HiCMAE

[Information Fusion 2024] HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition

Language:PythonMIT77 1 7

DCASE2021_task6_v2

Code for CVSSP submission to DCASE 2021 Task 6

Language:Jupyter Notebook34 2 7

MobileVLM

Implementation of the LDP module block in PyTorch and Zeta from the paper: "MobileVLM: A Fast, Strong and Open Vision Language Assistant for Mobile Devices"

Language:PythonMIT1300

Recurrent-Linear-Transformers

Implementation of Recurrent Linear Transformers in Jax+Flax.

Language:PythonApache-2.013 4 2

NoAudioCaptioning

Repository for "Training Audio Captioning Models without Audio"

NOASSERTION9 40

MERTools

Toolkits for Multimodal Emotion Recognition

Language:Python400