gg-hf

Enterprise

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

clefourrier authored a paper 19 days ago

Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation

giffmana authored a paper 20 days ago

PaliGemma 2: A Family of Versatile VLMs for Transfer

reach-vb authored a paper about 2 months ago

Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis

View all activity

gg-hf's activity

akhaliq

posted an update 6 days ago

Post

2366

Google drops Gemini 2.0 Flash Thinking

a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more

now available in anychat, try it out: akhaliq/anychat

Xenova

posted an update 7 days ago

Post

1891

Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser!
🚀 Faster and more accurate than Whisper
🔒 Privacy-focused (no data leaves your device)
⚡️ WebGPU accelerated (w/ WASM fallback)
🔥 Powered by ONNX Runtime Web and Transformers.js

Demo: webml-community/moonshine-web
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/moonshine-web

Narsil

posted an update 13 days ago

Post

936

Performance leap: TGI v3 is out. Processes 3x more tokens, 13x faster than vLLM on long prompts. Zero config !

3x more tokens.

By reducing our memory footprint, we’re able to ingest many more tokens and more dynamically than before. A single L4 (24GB) can handle 30k tokens on llama 3.1-8B, while vLLM gets barely 10k. A lot of work went into reducing the footprint of the runtime and its effect are best seen on smaller constrained environments.
13x faster

On long prompts (200k+ tokens) conversation replies take 27.5s in vLLM, while it takes only 2s in TGI. How so ? We keep the initial conversation around, so when a new reply comes in, we can answer almost instantly. The overhead of the lookup is ~5us. Thanks @Dani ël de Kok for the beast data structure.
Zero config

That’s it. Remove all the flags your are using and you’re likely to get the best performance. By evaluating the hardware and model, TGI carefully selects automatic values to give best performance. In production, we don’t have any flags anymore in our deployments. We kept all existing flags around, they may come in handy in niche scenarios.

Read more: https://huggingface.co./docs/text-generation-inference/conceptual/chunking

Xenova

posted an update 17 days ago

Post

2516

Introducing TTS WebGPU: The first ever text-to-speech web app built with WebGPU acceleration! 🔥 High-quality and natural speech generation that runs 100% locally in your browser, powered by OuteTTS and Transformers.js. 🤗 Try it out yourself!

Demo: webml-community/text-to-speech-webgpu
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/text-to-speech-webgpu
Model: onnx-community/OuteTTS-0.2-500M (ONNX), OuteAI/OuteTTS-0.2-500M (PyTorch)

ariG23498

posted an update 20 days ago

Post

1283

We are blessed with another iteration of Pali Gemma. Google launches PaliGemma 2.

google/paligemma-2-release-67500e1e1dbfdd4dee27ba48

merve/paligemma2-vqav2

giffmana

authored a paper 20 days ago

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published 21 days ago • 118

Xenova

posted an update 27 days ago

Post

3917

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:
🔀 Janus from Deepseek for unified multimodal understanding and generation (Text-to-Image and Image-Text-to-Text)
👁️ Qwen2-VL from Qwen for dynamic-resolution image understanding
🔢 JinaCLIP from Jina AI for general-purpose multilingual multimodal embeddings
🌋 LLaVA-OneVision from ByteDance for Image-Text-to-Text generation
🤸‍♀️ ViTPose for pose estimation
📄 MGP-STR for optical character recognition (OCR)
📈 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. 👇
https://github.com/huggingface/transformers.js/releases/tag/3.1.0

Demo link (+ source code): webml-community/Janus-1.3B-WebGPU

akhaliq

posted an update 28 days ago

Post

3795

QwQ-32B-Preview is now available in anychat

A reasoning model that is competitive with OpenAI o1-mini and o1-preview

try it out: akhaliq/anychat

1 reply

akhaliq

posted an update 28 days ago

Post

3674

New model drop in anychat

allenai/Llama-3.1-Tulu-3-8B is now available

try it here: akhaliq/anychat

akhaliq

posted an update about 1 month ago

Post

2665

anychat

supports chatgpt, gemini, perplexity, claude, meta llama, grok all in one app

try it out there: akhaliq/anychat

SaylorTwift

posted an update about 1 month ago

Post

386

How do I test an LLM for my unique needs?
If you work in finance, law, or medicine, generic benchmarks are not enough.
This blog post uses Argilla, Distilllabel and 🌤️Lighteval to generate evaluation dataset and evaluate models.

https://github.com/argilla-io/argilla-cookbook/blob/main/domain-eval/README.md

Xenova

posted an update about 1 month ago

Post

5517

Have you tried out 🤗 Transformers.js v3? Here are the new features:
⚡ WebGPU support (up to 100x faster than WASM)
🔢 New quantization formats (dtypes)
🏛 120 supported architectures in total
📂 25 new example projects and templates
🤖 Over 1200 pre-converted models
🌐 Node.js (ESM + CJS), Deno, and Bun compatibility
🏡 A new home on GitHub and NPM

Get started with npm i @huggingface/transformers.

Learn more in our blog post: https://huggingface.co./blog/transformersjs-v3

3 replies

ArthurZ

posted an update about 1 month ago

Post

2671

Native tensor parallel has landed in transformers!!! https://github.com/huggingface/transformers/pull/34184 thanks a lot to the torch team for their support!

Contributions are welcome to support more models! 🔥

ariG23498

posted an update about 1 month ago

Post

2831

Qwen/qwen25-66e81a666513e518adb90d9e

Qwen/Qwen2.5-Coder-Artifacts

Qwen/Qwen2.5-Coder-demo

lvwerra

authored a paper about 2 months ago

SelfCodeAlign: Self-Alignment for Code Generation

Paper • 2410.24198 • Published Oct 31 • 21

ariG23498

posted an update 2 months ago

Post

1578

Cohere drops two new multilingual models!

CohereForAI/aya-expanse-8b
CohereForAI/aya-expanse-32b

Try them out here

CohereForAI/aya_expanse

RyanMullins

updated a Space 2 months ago

Running on L40S

🏃

SynthID Text

Watermarking LLM-generated text with SynthID Text

joaogante

updated a Space 2 months ago

Running on L40S

🏃

SynthID Text

Watermarking LLM-generated text with SynthID Text

ariG23498

posted an update 4 months ago

Post

1612

You can now use DoRA for your embedding layers!

PR: https://github.com/huggingface/peft/pull/2006

I have documented my journey of this specific PR in a blog post for everyone to read. The highlight of the PR was when the first author of DoRA reviewed my code.

Blog Post: https://huggingface.co./blog/ariG23498/peft-dora

Huge thanks to @BenjaminB for all the help I needed.

Xenova

posted an update 4 months ago

Post

13910

I can't believe this... Phi-3.5-mini (3.8B) running in-browser at ~90 tokens/second on WebGPU w/ Transformers.js and ONNX Runtime Web! 🤯 Since everything runs 100% locally, no messages are sent to a server — a huge win for privacy!
- 🤗 Demo: webml-community/phi-3.5-webgpu
- 🧑‍💻 Source code: https://github.com/huggingface/transformers.js-examples/tree/main/phi-3.5-webgpu

11 replies

AI & ML interests

Recent Activity

Team members 118

gg-hf's activity

SynthID Text

SynthID Text