HNHacker News
TopNewBestAskShowJobs

xenova

668 karma · joined March 17, 2023

submissionscomments

Bonsai 27B: A 27B-Class model that runs on a phone

prismml.com·706 pts·xenova·
250

1-Bit and Ternary Bonsai Image 4B: Image Generation for Local Devices

prismml.com·3 pts·xenova·
0

ML-intern: open-source ML engineer that reads papers, trains and ships models

github.com·3 pts·xenova·
0

Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser

huggingface.co·227 pts·xenova·
53

Transformers.js v3: WebGPU Support, New Models and Tasks, and More

huggingface.co·1 pts·xenova·
0

SAM 2: Segment Anything in Images and Videos

github.com·824 pts·xenova·
147

PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding

github.com·1 pts·xenova·
0

Mamba: New SSM arch with linear-time scaling that outperforms Transformers

github.com·6 pts·xenova·
2

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

huggingface.co·2 pts·xenova·
1

Making real-time ML-powered web games with Transformers.js

huggingface.co·2 pts·xenova·
1

MMS: Scaling Speech Technology to 1000 languages demo

huggingface.co·1 pts·xenova·
0

Whisper Web: ML-powered speech recognition in the browser

twitter.com·3 pts·xenova·
1