nltpt

Enterprise
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

nltpt's activity

Xenova 
posted an update 10 days ago
Xenova 
posted an update 22 days ago
view post
Post
2549
Reasoning models like o3 and o4-mini are advancing faster than ever, but imagine what will be possible when they can run locally in your browser! 🤯

Well, with 🤗 Transformers.js, you can do just that! Here's Zyphra's new ZR1 model running at over 100 tokens/second on WebGPU! ⚡️

Giving models access to browser APIs (like File System, Screen Capture, and more) could unlock an entirely new class of web experiences that are personalized, interactive, and run locally in a secure, sandboxed environment.

For now, try out the demo! 👇
webml-community/Zyphra-ZR1-WebGPU
  • 1 reply
·
eliebak 
posted an update about 2 months ago
view post
Post
1727
Google just dropped an exciting technical report for the brand-new Gemma3 model! 🚀 Here are my personal notes highlighting the most intriguing architectural innovations, design choices, and insights from this release:

1) Architecture choices:
> No more softcaping, replace by QK-Norm
> Both Pre AND Post Norm
> Wider MLP than Qwen2.5, ~ same depth
> SWA with 5:1 and 1024 (very small and cool ablation on the paper!)
> No MLA to save KV cache, SWA do the job!

2) Long context
> Only increase the rope in the global layer (to 1M)
> Confirmation that it's harder to do long context for smol models, no 128k for the 1B
> Pretrained with 32k context? seems very high
> No yarn nor llama3 like rope extension

3) Distillation
> Only keep te first 256 logits for the teacher
> Ablation on the teacher gap (tl;dr you need some "patience" to see that using a small teacher is better)
> On policy distillation yeahh (by
@agarwl_
et al), not sure if the teacher gap behave the same here, curious if someone have more info?

4) Others
> Checkpoint with QAT, that's very cool
> RL using improve version of BOND, WARM/WARP good excuse to look at
@ramealexandre
papers
> Only use Zero3, no TP/PP if i understand correctly ?
> Training budget relatively similar than gemma2
  • 1 reply
·
alvarobartt 
posted an update 2 months ago
view post
Post
3101
🔥 Agents can do anything! @microsoft Research just announced the release of Magma 8B!

Magma is a new Visual Language Model (VLM) with 8B parameters for multi-modal agents designed to handle complex interactions across virtual and real environments; and it's MIT licensed!

Magma comes with exciting new features such as:
- Introduces the Set-of-Mark and Trace-of-Mark techniques for fine-tuning
- Leverages a large amount of unlabeled video data to learn the spatial-temporal grounding and planning
- A strong generalization and ability to be fine-tuned for other agentic tasks
- SOTA in different multi-modal benchmarks spanning across UI navigation, robotics manipulation, image / video understanding and spatial understanding and reasoning
- Generates goal-driven visual plans and actions for agentic use cases

Model: microsoft/Magma-8B
Technical Report: Magma: A Foundation Model for Multimodal AI Agents (2502.13130)
Xenova 
posted an update 3 months ago
view post
Post
13271
We did it. Kokoro TTS (v1.0) can now run 100% locally in your browser w/ WebGPU acceleration. Real-time text-to-speech without a server. ⚡️

Generate 10 seconds of speech in ~1 second for $0.

What will you build? 🔥
webml-community/kokoro-webgpu

The most difficult part was getting the model running in the first place, but the next steps are simple:
✂️ Implement sentence splitting, allowing for streamed responses
🌍 Multilingual support (only phonemization left)

Who wants to help?
·
Xenova 
posted an update 4 months ago
view post
Post
7361
Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by 🤗 Transformers.js. WebGPU support coming soon!
👉 npm i kokoro-js 👈

Try it out yourself: webml-community/kokoro-web
Link to models/samples: onnx-community/Kokoro-82M-ONNX

You can get started in just a few lines of code!
import { KokoroTTS } from "kokoro-js";

const tts = await KokoroTTS.from_pretrained(
  "onnx-community/Kokoro-82M-ONNX",
  { dtype: "q8" }, // fp32, fp16, q8, q4, q4f16
);

const text = "Life is like a box of chocolates. You never know what you're gonna get.";
const audio = await tts.generate(text,
  { voice: "af_sky" }, // See `tts.list_voices()`
);
audio.save("audio.wav");

Huge kudos to the Kokoro TTS community, especially taylorchu for the ONNX exports and Hexgrad for the amazing project! None of this would be possible without you all! 🤗

The model is also extremely resilient to quantization. The smallest variant is only 86 MB in size (down from the original 326 MB), with no noticeable difference in audio quality! 🤯
·
Xenova 
posted an update 4 months ago
Xenova 
posted an update 5 months ago
view post
Post
4372
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 5 months ago
view post
Post
1594
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 5 months ago
view post
Post
3374
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)