161

Bonsai 27B: A 27B-Class model that runs on a phone (prismml.com)

3 hours ago xenova prismml.com

2

1-Bit and Ternary Bonsai Image 4B: Image Generation for Local Devices (prismml.com)

a month ago xenova prismml.com

1

ML-intern: open-source ML engineer that reads papers, trains and ships models (github.com/huggingface)

3 months ago xenova github.com

75

Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser (huggingface.co)

a year ago xenova huggingface.co

1

Transformers.js v3: WebGPU Support, New Models and Tasks, and More (huggingface.co)

a year ago xenova huggingface.co

189

SAM 2: Segment Anything in Images and Videos (github.com/facebookresearch)

a year ago xenova github.com

1

PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding (github.com/tencentarc)

2 years ago xenova github.com

7

Mamba: New SSM arch with linear-time scaling that outperforms Transformers (github.com/state-spaces)

2 years ago xenova github.com

2

Count tokens used by GPT-4 and Llama for large texts (> 50k characters) (huggingface.co)

2 years ago xenova huggingface.co

2

Making real-time ML-powered web games with Transformers.js (huggingface.co)

3 years ago xenova huggingface.co

1

MMS: Scaling Speech Technology to 1000 languages demo (huggingface.co)

3 years ago xenova huggingface.co

4

Whisper Web: ML-powered speech recognition in the browser (twitter.com/xenovacom)

3 years ago xenova twitter.com