huggingfacejs (Huggingface.js)

merve

posted an update about 3 hours ago

Post

64

we've merged LightGlue keypoint matcher to Hugging Face transformers! it allows commercial use when paired with an open-source keypoint detector 🙏🏻

it works very well, try it yourself: ETH-CVG/LightGlue

here's an in-the-wild test with two images of the same place ⤵️

1 reply

·

merve

posted an update 1 day ago

Post

2160

Release picks of the past week is here! Find more models, datasets, Spaces here merve/june-20-releases-68594824d1f4dfa61aee3433

🖼️ VLMs/OCR
> moonshotai/Kimi-VL-A3B-Thinking-2506 is a powerful reasoning vision LM, 3B active params, smarter with less tokens, supports long documents, videos 👏 (OS)
> nanonets/Nanonets-OCR-s is 3.75B params OCR model based on Qwen2.5VL-3B-Instruct (OS)

💬 LLMs
> moonshotai/Kimi-Dev-72B is a strong coding model based on Qwen2.5-72B (OS)
> Mistral released mistralai/Mistral-Small-3.2-24B-Instruct-2506, an update to their former model with better function calling & instruction following (OS)

🗣️ Audio
> Google released google/magenta-realtime, real time music generation & audio synthesis (cc-by-4)
> kyutai released new speech-to-text models that come in 1B & 2B ( kyutai/stt-1b-en_fr, stt-2b-en_fr) with 0.5s and 2.5s delay

3D
> Tencent released tencent/Hunyuan3D-2.1 an image-to-3D model (see below)

merve

posted an update 2 days ago

Post

4732

fav open-source multimodal reasoning model just got an update 🔥

moonshotai/Kimi-VL-A3B-Thinking-2506 has
> smarter with less tokens, small size (only 3B active params!!!)
> better accuracy
> video reasoning
> higher resolution 🤯
Read their blog https://huggingface.co/blog/moonshotai/kimi-vl-a3b-thinking-2506

merve

posted an update 4 days ago

Post

2165

y'all have been asking my opinion on how OCR models compare to each other 👀
I will leave three apps to compare newest models by @prithivMLmods instead ⤵️
> compare Nanonets-OCR-s, Qwen2-VL-OCR-2B-Instruct, RolmOCR, Aya-Vision prithivMLmods/Multimodal-OCR
> SmolDocling, Nanonets-OCR-s, MonkeyOCR, Typhoon-OCR-7B prithivMLmods/Multimodal-OCR2
> docscopeOCR, MonkeyOCR, coreOCR prithivMLmods/core-OCR

1 reply

·

coyotte508

updated a Space 5 days ago

Better Auth Test

🏢

Authenticate using Hugging Face

coyotte508

published a Space 5 days ago

Better Auth Test

🏢

Authenticate using Hugging Face

merve

posted an update 5 days ago

Post

1823

stop using VLMs blindly ✋🏻

compare different VLM outputs on a huge variety of inputs (from reasoning to OCR!) 🔥 visionLMsftw/comparevlms

> has support for multiple VLMs: google/gemma-3-27b-it, Qwen/Qwen2.5-VL-7B-Instruct, Qwen/Qwen2.5-VL-32B-Instruct, meta-llama/Llama-4-Maverick-17B-128E-Instruct, HuggingFaceTB/SmolVLM2-2.2B-Instruct
> recommend us new models or inputs, we'll add 🫡

so far I figured out
> for fact-checks, you need a relatively bigger size (7B is ok!)
> Gemma 3 gets downgrade without pan and scan (especially for 📑)
> Qwen2.5VL-32B is very talkative, great for reasoning but not good for simple tasks 🗣️

2 replies

·

merve

posted an update 6 days ago

Post

3537

Releases of the past week are here merve/releases-june-13-6852c3c1eaf1e0c24c958860

Here's our picks 🤓
So many interesting models released past week in open AI! 🤖

🖼️ Computer Vision/VLMs
> nanonets/Nanonets-OCR-s is the new state-of-the-art OCR model that can handle checkboxes, watermarks, tables (OS)
> Meta released facebook/v-jepa-2-6841bad8413014e185b497a6, new sota video embeddings with two new classification models (OS)
> ByteDance-Seed/SeedVR2-3B is a new 3B video restoration model (OS)

Audio
> Stepfun released stepfun-ai/Step-Audio-AQAA, new large (137B 🤯) audio language model that takes in audio and generates audio (OS)

🤖 Robotics
> nvidia released nvidia/GR00T-N1.5-3B, new open foundation vision language action model

3D
> tencent/Hunyuan3D-2.1 is the new version of Hunyuan by Tencent that can generate 3D assets from text and image prompts

merve

posted an update 7 days ago

Post

3486

IN: video fine-tuning support for

facebook V-JEPA 2 in HF transformers 🔥

it comes with
> four models fine-tuned on Diving48 and SSv2 dataset facebook/v-jepa-2-6841bad8413014e185b497a6
> FastRTC demo on V-JEPA2 SSv2 qubvel-hf/vjepa2-streaming-video-classification
> fine-tuning script on UCF-101 https://gist.github.com/ariG23498/28bccc737c11d1692f6d0ad2a0d7cddb
> fine-tuning notebook on UCF-101 https://colab.research.google.com/drive/16NWUReXTJBRhsN3umqznX4yoZt2I7VGc?usp=sharing
we're looking forward to see what you will build! 🤗

merve

posted an update 8 days ago

Post

2408

#CVPR2025 Paper Picks #1
VisionZip is a compression technique that reduces number of visual tokens to improve performance AND prefill time for vision language models
demo: Senqiao/VisionZip
paper: VisionZip: Longer is Better but Not Necessary in Vision Language Models (2412.04467)
most of the image tokens are redundant for the LLM, so the authors ask "are all visual tokens necessary?"

the method is simple:
find which tokens have the highest attention score, merge rest of the tokens based on similarity, then merge both

their method is both training-free and for fine-tuning
the authors report 5 point improvement on average of vision language tasks + 8x improvement in prefilling time for Llava-Next 7B and 13B 🤯

removing redundant tokens improve image token quality too 🥹

merve

posted an update 8 days ago

Post

3629

stop writing CUDA kernels yourself

we have launched Kernel Hub: easy optimized kernels for all models on Hugging Face 🔥 use them right away!
it's where the community populates optimized kernels 🤝

this release comes in three parts
> Kernel Hub: contains (as of now) 14 kernels
> kernels: Python library to load kernels from Kernel Hub
> kernel-builder: Nix package to build kernels for PyTorch (made using PyTorch C++ frontend)

when building models, your regular workflow should be pulling kernels from Hub and building your model with them 🤗
here's a practical example with RMSNorm:
1. pull the kernel from Hub with get_kernel
2. decorate with use_kernel_forward_from_hub
3. inject it to your model
we'd love to hear your feedback! 🙏🏻
we also welcome kernel contributions by community 🥹💗

- request kernels here: kernels-community/README#1
- check out this org:

kernels-community
- read the blog: https://huggingface.co/blog/hello-hf-kernels

1 reply

·

merve

posted an update 11 days ago

Post

688

Dolphin: new OCR model by ByteDance with MIT license 🐬

the model first detects element in the layout (table, formula etc) and then parses each element in parallel for generation
Model: ByteDance/Dolphin
Try the demo: ByteDance/Dolphin

merve

posted an update 13 days ago

Post

1361

stop building parser pipelines 👋🏻
there's a new document parser that is small, fast, Apache 2.0 licensed and is better than all the other ones! 😱

echo840/MonkeyOCR is a 3B model that can parse everything (charts, formules, tables etc) in a document 🤠
> the authors show in the paper that document parsing pipelines often have errors propagating back
> using singular e2e models are better but they're too heavy to use

this model addresses both: it's lighter, faster, stronger 🔥

merve

posted an update 13 days ago

Post

1593

Meta just released V-JEPA 2: new open-source image/video world models ⏯️🤗 facebook/v-jepa-2-6841bad8413014e185b497a6

> based on ViT, different sizes (L/G/H) and resolution (286/384)
> 0-day support in 🤗 transformers
> comes with a physical reasoning (from video) benchmark: MVPBench, IntPhys 2, and CausalVQA facebook/physical_reasoning_leaderboard

Read more https://ai.meta.com/blog/v-jepa-2-world-model-benchmarks/
We will release a fine-tuning notebook with task-specific models in transformers format soon, stay tuned!

merve

posted an update 19 days ago

Post

2862

Qwen2.5-Omni is soooo good that people build multimodal reasoning models off of it 🥹
> KE-Team/Ke-Omni-R-3B is open-source audio reasoning model sota on average of benchmarks, based on Qwen/Qwen2.5-Omni-3B 🗣️
> Haoz0206/Omni-R1 is a video reasoning model with pixel level grounding (see below) and it's super competitive ⏯️ based on Qwen/Qwen2.5-Omni-7B

Xenova

posted an update 20 days ago

Post

4019

NEW: Real-time conversational AI models can now run 100% locally in your browser! 🤯

🔐 Privacy by design (no data leaves your device)
💰 Completely free... forever
📦 Zero installation required, just visit a website
⚡️ Blazingly-fast WebGPU-accelerated inference

Try it out: webml-community/conversational-webgpu

For those interested, here's how it works:
- Silero VAD for voice activity detection
- Whisper for speech recognition
- SmolLM2-1.7B for text generation
- Kokoro for text to speech

Powered by Transformers.js and ONNX Runtime Web! 🤗 I hope you like it!

3 replies

·

merve

posted an update 20 days ago

Post

1520

Past week was insanely packed for open AI! 😱
Luckily we picked some highlights for you ❤️ lfg!

💬 LLMs/VLMs
> Deepseek 🐳 released deepseek-ai/DeepSeek-R1-0528, 38B model, only 0.2 and 1.4 points behind o3 in AIME 24/25 🤯 they also released an 8B distilled version based on Qwen3 (OS) deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d
> Xiaomi released MiMo-7B-RL (LLM for code and math) and MiMo-VL-7B-RL (VLM for visual reasoning, GUI agentic task and general use) (OS) 😍 XiaomiMiMo/mimo-vl-68382ccacc7c2875500cd212
> NVIDIA released , new reasoning model nvidia/Nemotron-Research-Reasoning-Qwen-1.5B
> DS: MiniMax released https://huggingface.co/MiniMaxAI/SynLogic, new 49k logical reasoning examples across 35 tasks including solving cipher, sudoku and more!

🖼️ Image/Video Generation
> tencent released tencent/HunyuanPortrait, a new model for consistent portrait generation with SVD Research license. They also released tencent/HunyuanVideo-Avatar, audio driven avatar generation (OS)
> showlab released showlab/OmniConsistency, consistent stylization model (OS)
> Rapidata/text-2-video-human-preferences-veo3 is a new T2V preference dataset based on videos from Veo3 with 46k examples (OS)

Audio🗣️
> https://huggingface.co/ResembleAI/Chatterbox is a new 500M text-to-speech model preferred more than ElevenLabs (OS) 😍
> PlayHT/PlayDiffusion is a new speech editing model (OS)

Other
> https://huggingface.co/NX-AI/TiReX is a new time series foundation model
> Yandex released a huge (4.79B examples!) video recommendation dataset https://huggingface.co/yandex/yambda

OS ones have Apache2.0 or MIT licenses, find more models and datasets here merve/releases-30-may-6840097345e0b1e915bff843