SmolVLM: Redefining small and efficient multimodal models
Paper
•
2504.05299
•
Published
•
135
nltpt
Enterprise
AI & ML interests
None defined yet.
Recent Activity
View all activity
nltpt's activity
eliebak
authored
a
paper
1 day ago
Xenova
authored
a
paper
1 day ago
reach-vb
authored
a
paper
1 day ago
rosbo
authored
a
paper
12 days ago
edbeeching
authored
a
paper
28 days ago
Post
1630
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) 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
Post
6188
SmolVLM-2 and SigLIP-2 are now part of
They're added on top of the v4.49.0 release, and can be installed from the following tags:
This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures).
Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models.
Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.
transformers in dedicated releases!They're added on top of the v4.49.0 release, and can be installed from the following tags:
v4.49.0-SmolVLM-2 and v4.49.0-SigLIP-2.This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures).
Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models.
Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.
-
- 1 reply
Post
12410
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?
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?
- 11 replies
eliebak
authored
a
paper
2 months ago
reach-vb
authored
a
paper
2 months ago
eliebak
authored
a
paper
2 months ago
Xenova
authored
a
paper
2 months ago
Post
2474
Tried my hand at simplifying the derivations of Direct Preference Optimization.
I cover how one can reformulate RLHF into DPO. The idea of implicit reward modeling is chef's kiss.
Blog: https://huggingface.co/blog/ariG23498/rlhf-to-dpo
I cover how one can reformulate RLHF into DPO. The idea of implicit reward modeling is chef's kiss.
Blog: https://huggingface.co/blog/ariG23498/rlhf-to-dpo
Post
6936
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!
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! 🤯
👉 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! 🤯
-
- 14 replies
Post
1982
Timm ❤️ Transformers
Wtih the latest version of transformers you can now use any timm model with the familiar transformers API.
Blog Post: https://huggingface.co/blog/timm-transformers
Repository with examples: https://github.com/ariG23498/timm-wrapper-examples
Collection: ariG23498/timmwrapper-6777b85f1e8d085d3f1374a1
Wtih the latest version of transformers you can now use any timm model with the familiar transformers API.
Blog Post: https://huggingface.co/blog/timm-transformers
Repository with examples: https://github.com/ariG23498/timm-wrapper-examples
Collection: ariG23498/timmwrapper-6777b85f1e8d085d3f1374a1
mryab
authored
a
paper
3 months ago
Post
8400
First project of 2025: Vision Transformer Explorer
I built a web app to interactively explore the self-attention maps produced by ViTs. This explains what the model is focusing on when making predictions, and provides insights into its inner workings! 🤯
Try it out yourself! 👇
webml-community/attention-visualization
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/attention-visualization
I built a web app to interactively explore the self-attention maps produced by ViTs. This explains what the model is focusing on when making predictions, and provides insights into its inner workings! 🤯
Try it out yourself! 👇
webml-community/attention-visualization
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/attention-visualization
Post
4303
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
🚀 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
-
- 5 replies
Post
3330
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)
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)
Post
6281
VLMs are going through quite an open revolution AND on-device friendly sizes:
1. Google DeepMind w/ PaliGemma2 - 3B, 10B & 28B: google/paligemma-2-release-67500e1e1dbfdd4dee27ba48
2. OpenGVLabs w/ InternVL 2.5 - 1B, 2B, 4B, 8B, 26B, 38B & 78B: https://huggingface.co/collections/OpenGVLab/internvl-25-673e1019b66e2218f68d7c1c
3. Qwen w/ Qwen 2 VL - 2B, 7B & 72B: Qwen/qwen2-vl-66cee7455501d7126940800d
4. Microsoft w/ FlorenceVL - 3B & 8B: @jiuhai
5. Moondream2 w/ 0.5B: https://huggingface.co/vikhyatk/
What a time to be alive! 🔥
1. Google DeepMind w/ PaliGemma2 - 3B, 10B & 28B: google/paligemma-2-release-67500e1e1dbfdd4dee27ba48
2. OpenGVLabs w/ InternVL 2.5 - 1B, 2B, 4B, 8B, 26B, 38B & 78B: https://huggingface.co/collections/OpenGVLab/internvl-25-673e1019b66e2218f68d7c1c
3. Qwen w/ Qwen 2 VL - 2B, 7B & 72B: Qwen/qwen2-vl-66cee7455501d7126940800d
4. Microsoft w/ FlorenceVL - 3B & 8B: @jiuhai
5. Moondream2 w/ 0.5B: https://huggingface.co/vikhyatk/
What a time to be alive! 🔥