Xenova: We just released Transformers.js v3.1 and you're not going to believe what's now possible in the browser w/ WebGPU! 🤯 Let's take a look: 1. Janus from Deepseek for unified multimodal understanding and generation (Text-to-Image and Image-Text-to-Text) Demo (+ source code): hf.co/spaces/webml...

Xenova xenova.bsky.social
We just released Transformers.js v3.1 and you're not going to believe what's now possible in the browser w/ WebGPU! 🤯 Let's take a look: 1. Janus from Deepseek for unified multimodal understanding and generation (Text-to-Image and Image-Text-to-Text) Demo (+ source code): hf.co/spaces/webml...
Nov 28, 2024 15:13
0 reposts 0 quotes 0 likes

View on Bluesky Download video Show all post labels
Xenova xenova.bsky.social · Nov 28, 2024
2. Qwen2-VL from Qwen for dynamic-resolution image understanding 3. JinaCLIP from Jina AI for general-purpose multilingual multimodal embeddings 4. LLaVA-OneVision from ByteDance for Image-Text-to-Text generation 5. ViTPose for pose estimation

View on Bluesky Show all post labels
Xenova xenova.bsky.social · Nov 28, 2024
6. MGP-STR for optical character recognition (OCR) 7. PatchTST & PatchTSMixer for time series forecasting That's right, everything running 100% locally in your browser (no data sent to a server)! 🔥 Huge for privacy! Check out the release notes for more information. 👇 github.com/huggingface/...
Release 3.1.0 · huggingface/transformers.js

🚀 Transformers.js v3.1 — any-to-any, text-to-image, image-to-text, pose estimation, time series forecasting, and more! Table of contents: 🤖 New models: Janus, Qwen2-VL, JinaCLIP, LLaVA-OneVision, ...

github.com

View on Bluesky Show all post labels

An unhandled error has occurred. Reload 🗙

Release 3.1.0 · huggingface/transformers.js