hf-maintainers (HF Canonical Model Maintainers)

lewtun

posted an update 1 day ago

Post

2441

Introducing OpenR1-Math-220k!

open-r1/OpenR1-Math-220k

The community has been busy distilling DeepSeek-R1 from inference providers, but we decided to have a go at doing it ourselves from scratch 💪

What’s new compared to existing reasoning datasets?

♾ Based on AI-MO/NuminaMath-1.5: we focus on math reasoning traces and generate answers for problems in NuminaMath 1.5, an improved version of the popular NuminaMath-CoT dataset.

🐳 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.

📀 512 H100s running locally: Instead of relying on an API, we leverage vLLM and SGLang to run generations locally on our science cluster, generating 180k reasoning traces per day.

⏳ Automated filtering: We apply Math Verify to only retain problems with at least one correct answer. We also leverage Llama3.3-70B-Instruct as a judge to retrieve more correct examples (e.g for cases with malformed answers that can’t be verified with a rules-based parser)

📊 We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.

🔎 Read our blog post for all the nitty gritty details: https://huggingface.co/blog/open-r1/update-2

merve

posted an update 4 days ago

Post

2473

Interesting releases in open AI this week, let's recap 🤠 merve/feb-7-releases-67a5f7d7f172d8bfe0dd66f4

🤖 Robotics
> Pi0, first open-source foundation vision-language action model was released in Le Robot (Apache 2.0)

💬 LLMs
> Groundbreaking: s1 is simpler approach to test-time scaling, the release comes with small s1K dataset of 1k question-reasoning trace pairs (from Gemini-Thinking Exp) they fine-tune Qwen2.5-32B-Instruct to get s1-32B, outperforming o1-preview on math 🤯 s1-32B and s1K is out!
> Adyen released DABstep, a new benchmark along with it's leaderboard demo for agents doing data analysis
> Krutrim released Krutrim-2 instruct, new 12B model based on NeMo12B trained and aligned on Indic languages, a new multilingual sentence embedding model (based on STSB-XLM-R), and a translation model for Indic languages

👀 Multimodal
> PKU released Align-DS-V, a model aligned using their new technique called LLF for all modalities (image-text-audio), along with the dataset Align Anything
> OLA-7B is a new any-to-any model by Tencent that can take text, image, video, audio data with context window of 32k tokens and output text and speech in English and Chinese
> Krutrim released Chitrarth, a new vision language model for Indic languages and English

🖼️ Vision
> BiRefNet_HR is a new higher resolution BiRefNet for background removal

🗣️ Audio
> kyutai released Hibiki, it's a real-time speech-to-speech translation model 🤯 it's available for French-English translation
> Krutrim released Dhwani, a new STT model for Indic languages
> They also release a new dataset for STT-TTS

🖼️ Image Generation
> Lumina released Lumina-Image-2.0, a 2B parameter-flow based DiT for text to image generation
> Tencent released Hunyuan3D-2, a 3D asset generation model based on DiT and Hunyuan3D-Paint
> boreal-hl-v1 is a new boring photorealistic image generation LoRA based on Hunyuan

merve

posted an update 5 days ago

Post

2134

IBM released ibm-granite/granite-vision-3.1-2b-preview, a small vision LM with impressive performance on different tasks 😮🔥

it comes with transformers and vLLM support from the get-go 💗
you can run it in Colab T4, so I built a notebook to put it to test, find it here: https://github.com/merveenoyan/smol-vision/blob/main/inference_gists/IBM_Granite_Vision.ipynb

lewtun

authored a paper 5 days ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published 7 days ago • 154

merve

posted an update 11 days ago

Post

3781

This week in open AI was 🔥 Let's recap! 🤗 merve/january-31-releases-679a10669bd4030090c5de4d
LLMs 💬
> Huge: AllenAI released new Tülu models that outperform DeepSeek R1 using Reinforcement Learning with Verifiable Reward (RLVR) based on Llama 3.1 405B 🔥
> Mistral AI is back to open-source with their "small" 24B models (base & SFT), with Apache 2.0 license 😱
> Alibaba Qwen released their 1M context length models Qwen2.5-Instruct-1M, great for agentic use with Apache 2.0 license 🔥
> Arcee AI released Virtuoso-medium, 32.8B LLMs distilled from DeepSeek V3 with dataset of 5B+ tokens
> Velvet-14B is a new family of 14B Italian LLMs trained on 10T tokens in six languages
> OpenThinker-7B is fine-tuned version of Qwen2.5-7B-Instruct on OpenThoughts dataset

VLMs & vision 👀
> Alibaba Qwen is back with Qwen2.5VL, amazing new capabilities ranging from agentic computer use to zero-shot localization 🔥
> NVIDIA released new series of Eagle2 models with 1B and 9B sizes
> DeepSeek released Janus-Pro, new any-to-any model (image-text generation from image-text input) with MIT license
> BEN2 is a new background removal model with MIT license!

Audio 🗣️
> YuE is a new open-source music generation foundation model, lyrics-to-song generation

Codebase 👩🏻‍💻
> We are open-sourcing our SmolVLM training and eval codebase! https://github.com/huggingface/smollm/tree/main/vision
> Open-R1 is open-source reproduction of R1 by @huggingface science team https://huggingface.co/blog/open-r1

1 reply

·

davanstrien

posted an update 14 days ago

Post

1776

Why choose between strong LLM reasoning and efficient models?

Use DeepSeek to generate high-quality training data, then distil that knowledge into ModernBERT answerdotai/ModernBERT-base for fast, efficient classification.

Blog post: https://danielvanstrien.xyz/posts/2025/deepseek/distil-deepseek-modernbert.html

davanstrien

posted an update 15 days ago

Post

1866

Updated the ColPali Query Generator Space davanstrien/ColPali-Query-Generator to use Qwen/Qwen2.5-VL-7B-Instruct.

Given an input image, it generates several queries along with explanations to justify them. This approach can generate synthetic data for fine-tuning ColPali models.

davanstrien

posted an update 15 days ago

Post

2005

🌍 Big step for multilingual AI data!

The Hugging Face community has rated educational content in languages spoken by 1.6 billion people! New additions:
• Japanese
• Italian
• Old High German

Learn more and contribute: https://huggingface.co/blog/davanstrien/fineweb2-community

These ratings can help enhance training data for major world languages.

1 reply

·

lewtun

posted an update 17 days ago

Post

10044

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open!

🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.

🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code.

🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training.

Follow along: https://github.com/huggingface/open-r1

5 replies

·

merve

posted an update 18 days ago

Post

5095

Oof, what a week! 🥵 So many things have happened, let's recap! merve/jan-24-releases-6793d610774073328eac67a9

Multimodal 💬
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG 💗
- UI-TARS are new models by ByteDance to unlock agentic GUI control 🤯 in 2B, 7B and 72B
- Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B
- MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context
- Dataset: Yale released a new benchmark called MMVU
- Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark

LLMs 📖
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! 🤯
- Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B
- NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!)

Audio 🗣️
- Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B
- TangoFlux is a new audio generation model trained from scratch and aligned with CRPO

Image/Video/3D Generation ⏯️
- Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux
- tencent released Hunyuan3D-2, new 3D asset generation from images

7 replies

·

merve

posted an update 18 days ago

Post

2245

smolagents can see 🔥
we just shipped vision support to smolagents 🤗 agentic computers FTW

you can now:
💻 let the agent get images dynamically (e.g. agentic web browser)
📑 pass images at the init of the agent (e.g. chatting with documents, filling forms automatically etc)
with few LoC change! 🤯
you can use transformers models locally (like Qwen2VL) OR plug-in your favorite multimodal inference provider (gpt-4o, antrophic & co) 🤠

read our blog http://hf.co/blog/smolagents-can-see

florentgbelidji

posted an update 25 days ago

Post

1452

𝗣𝗹𝗮𝗻𝗻𝗶𝗻𝗴 𝗬𝗼𝘂𝗿 𝗡𝗲𝘅𝘁 𝗦𝗸𝗶 𝗔𝗱𝘃𝗲𝗻𝘁𝘂𝗿𝗲 𝗝𝘂𝘀𝘁 𝗚𝗼𝘁 𝗦𝗺𝗮𝗿𝘁𝗲𝗿: 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗔𝗹𝗽𝗶𝗻𝗲 𝗔𝗴𝗲𝗻𝘁!🏔️⛷️

With the big hype around AI agents these days, I couldn’t stop thinking about how AI agents could truly enhance real-world activities.
What sort of applications could we build with those AI agents: agentic RAG? self-correcting text-to-sql? Nah, boring…

Passionate about outdoors, I’ve always dreamed of a tool that could simplify planning mountain trips while accounting for all potential risks. That’s why I built 𝗔𝗹𝗽𝗶𝗻𝗲 𝗔𝗴𝗲𝗻𝘁, a smart assistant designed to help you plan safe and enjoyable itineraries in the French Alps and Pyrenees.

Built using Hugging Face's 𝘀𝗺𝗼𝗹𝗮𝗴𝗲𝗻𝘁𝘀 library, Alpine Agent combines the power of AI with trusted resources like 𝘚𝘬𝘪𝘵𝘰𝘶𝘳.𝘧𝘳 (https://skitour.fr/) and METEO FRANCE. Whether it’s suggesting a route with moderate difficulty or analyzing avalanche risks and weather conditions, this agent dynamically integrates data to deliver personalized recommendations.

In my latest blog post, I share how I developed this project—from defining tools and integrating APIs to selecting the best LLMs like 𝘘𝘸𝘦𝘯2.5-𝘊𝘰𝘥𝘦𝘳-32𝘉-𝘐𝘯𝘴𝘵𝘳𝘶𝘤𝘵, 𝘓𝘭𝘢𝘮𝘢-3.3-70𝘉-𝘐𝘯𝘴𝘵𝘳𝘶𝘤𝘵, or 𝘎𝘗𝘛-4.

⛷️ Curious how AI can enhance adventure planning? Try the app and share your thoughts: florentgbelidji/alpine-agent

👉 Want to build your own agents? Whether for cooking, sports training, or other passions, the possibilities are endless. Check out the blog post to learn more: https://huggingface.co/blog/florentgbelidji/alpine-agent

Many thanks to @m-ric for helping on building this tool with smolagents!

1 reply

·

merve

posted an update 25 days ago

Post

2573

Everything that happened this week in open AI, a recap 🤠 merve/jan-17-releases-678a673a9de4a4675f215bf5

👀 Multimodal
- MiniCPM-o 2.6 is a new sota any-to-any model by OpenBMB
(vision, speech and text!)
- VideoChat-Flash-Qwen2.5-2B is new video multimodal models by OpenGVLab that come in sizes 2B & 7B in resolutions 224 & 448
- ByteDance released larger SA2VA that comes in 26B parameters
- Dataset: VRC-Bench is a new diverse benchmark for multimodal LLM reasoning performance

💬 LLMs
- MiniMax-Text-01 is a new huge language model (456B passive 45.9B active params) by MiniMaxAI with context length of 4M tokens 🤯
- Dataset: Sky-T1-data-17k is a diverse dataset used to train Sky-T1-32B
- kyutai released Helium-1-Preview-2B is a new small multilingual LM
- Wayfarer-12B is a new LLM able to write D&D 🧙🏻‍♂️
- ReaderLM-v2 is a new HTML parsing model by Jina AI

- Dria released, Dria-Agent-a-3B, new agentic coding model (Pythonic function calling) based on Qwen2.5 Coder
- Unsloth released Phi-4, faster and memory efficient Llama 3.3

🖼️ Vision
- MatchAnything is a new foundation model for matching
- FitDit is a high-fidelity VTON model based on DiT architecture

🗣️ Audio
- OuteTTS-0.3-1B is a new multilingual text-to-speech model with voice cloning and emotion control capabilities

📖 Retrieval
- lightblue released a new reranker based on Qwen2.5 LB-reranker-0.5B-v1.0 that can handle 95+ languages
- cde-small-v2 is a new sota small retrieval model by
@jxm

merve

posted an update 26 days ago

Post

2009

New smolagents example landed on Hugging Face cookbook 🤠

Learn how to create an inventory managing multi-agent system with smolagents, MongoDB and DeepSeek Chat 📖 https://huggingface.co/learn/cookbook/mongodb_smolagents_multi_micro_agents

davanstrien

posted an update 29 days ago

Post

3059

Introducing scandi-fine-web-cleaner davanstrien/scandi-fine-web-cleaner, the first model trained on FineWeb-C community annotations!

FineWeb2 is a massive multilingual dataset for pre-training language models. Like any web-scale dataset, it contains low-quality content. How can we improve it?

Over the past months, an amazing community of 400+ annotators has been labelling content quality (using Argilla) across 23 languages through the FineWeb-C initiative.

Today, I'm happy to share the first classifier trained on this data.

🔍 What we've built:

- A lightweight classifier that efficiently removes low-quality content
- 90%+ precision demonstrated on Danish & Swedish
- Can process the 43M+ documents in Danish FineWeb2 with minimal compute

🌍 Why this matters: The approach can be reproduced for any of the 23 languages in FineWeb-C ( data-is-better-together/fineweb-c). We can improve training data quality at scale without massive compute resources by starting with community annotations and training small, efficient classifiers.

Want to build a classifier for your language? Check out the full blog post with code examples and implementation details: https://danielvanstrien.xyz/posts/2025/FineWeb-c/scandinavian-content-filtering-fineweb.html

1 reply

·

merve

posted an update 30 days ago

Post

3878

there's a new multimodal retrieval model in town 🤠
LlamaIndex released vdr-2b-multi-v1
> uses 70% less image tokens, yet outperforming other dse-qwen2 based models
> 3x faster inference with less VRAM 💨
> shrinkable with matryoshka 🪆
> can do cross-lingual retrieval!
Collection: llamaindex/visual-document-retrieval-678151d19d2758f78ce910e1 (with models and datasets)
Demo: llamaindex/multimodal_vdr_demo
Learn more from their blog post here https://huggingface.co/blog/vdr-2b-multilingual 📖

merve

posted an update about 1 month ago

Post

3635

What a beginning to this year in open ML 🤠
Let's unwrap! merve/jan-10-releases-677fe34177759de0edfc9714

Multimodal 🖼️
> ByteDance released SA2VA: a family of vision LMs that can take image, video, text and visual prompts
> moondream2 is out with new capabilities like outputting structured data and gaze detection!
> Dataset: Alibaba DAMO lab released multimodal textbook — 22k hours worth of samples from instruction videos 🤯
> Dataset: SciCap captioning on scientific documents benchmark dataset is released along with the challenge!

LLMs 💬
> Microsoft released Phi-4, sota open-source 14B language model 🔥
> Dolphin is back with Dolphin 3.0 Llama 3.1 8B 🐬🐬
> Prime-RL released Eurus-2-7B-PRIME a new language model trained using PRIME alignment
> SmallThinker-3B is a new small reasoning LM based on Owen2.5-3B-Instruct 💭
> Dataset: QWQ-LONGCOT-500K is the dataset used to train SmallThinker, generated using QwQ-32B-preview 📕
> Dataset: @cfahlgren1 released React Code Instructions: a dataset of code instruction-code pairs 📕
> Dataset: Qwen team is on the roll, they just released CodeElo, a dataset of code preferences 👩🏻‍💻

Embeddings 🔖
> @MoritzLaurer released zero-shot version of ModernBERT large 👏
> KaLM is a new family of performant multilingual embedding models with MIT license built using Qwen2-0.5B

Image/Video Generation ⏯️
> NVIDIA released Cosmos, a new family of diffusion/autoregressive World Foundation Models generating worlds from images, videos and texts 🔥
> Adobe released TransPixar: a new text-to-video model that can generate assets with transparent backgrounds (a first!)
> Dataset: fal released cosmos-openvid-1m Cosmos-tokenized OpenVid-1M with samples from OpenVid-1M

Others
> Prior Labs released TabPFNv2, the best tabular transformer is out for classification and regression
> Metagene-1 is a new RNA language model that can be used for pathogen detection, zero-shot embedding and genome understanding

davanstrien

posted an update about 1 month ago

Post

2237

The data-is-better-together/fineweb-c dataset is growing!

This week a few more languages have got 1,000 annotations for the educational quality of data from HuggingFaceFW/fineweb-2.

Why should you care?

The quality of pre-training data can have a big impact on the performance of downstream language models trained on that data ( HuggingFaceFW/blogpost-fineweb-v1).

Being able to filter by educational quality is on way of improving the quality of the data you use for training an LLM. Very importantly this approach can also reduce the amount of data needed for pertaining.

Why not use an LLM?

LLMs can be used to annotate educational quality for a subset of data. This data can then be used to train a smaller encoder only model to label the full dataset. However, this may not work well for languages outside of english. This is where fineweb-c (community) comes in.

The community is annotating the educational quality of fineweb2 data. Currently 114 languages have some annotations. These annotations will enable a number of things:

- Evaluate whether an LLM can label the educational quality for texts in that language well
- Directly be used for training quality classifiers
- Help discover other rules and huerisitcs for refining fineweb2 further for different languages.

This week the following languages where done:

Swedish thanks to: @Lauler @AntonVic @ohallstrom @bjarlestam @menbom @Ekgren @apsod

Ukrainian thanks to: @hannayukhymenko @robinhad @realPivo @RabotiahovDmytro @reciprocate

Assamese thanks to: @moyoor97 @Arpanjyoti @nawaf-helmi123 @pahigogoi1 @aelhence @kishorekashyap

Want to learn more: https://huggingface.co/blog/davanstrien/fineweb2-community

Contribute yourself here: data-is-better-together/fineweb-c

1 reply

·

merve

posted an update about 1 month ago

Post

1815

ByteDance just dropped SA2VA: a new family of vision LMs combining Qwen2VL/InternVL and SAM2 with MIT license 💗 ByteDance/sa2va-model-zoo-677e3084d71b5f108d00e093

> The models are capable of tasks involving vision-language understanding and visual referrals (referring segmentation) both for images and videos ⏯️

> The models come in 1B, 4B and 8B and are based on InternVL2.5 for base architecture and Qwen2, Qwen2.5 and InternLM2 for language model part (depending on the checkpoint)

> The model is very interesting, it has different encoders for different modalities each (visual prompt, text prompt, image and video) then it concatenates these to feed into LLM 💬

the output segmentation tokens are passed to SAM2, to sort of match text (captions or semantic classes) to masks ⤵️

> Their annotation pipeline is also interesting, they seems to use two open large vision LMs to refine the annotations, and have different levels of descriptions to provide consistency.

1 reply

·

lewtun

posted an update about 1 month ago

Post

3831

I was initially pretty sceptical about Meta's Coconut paper [1] because the largest perf gains were reported on toy linguistic problems. However, these results on machine translation are pretty impressive!

https://x.com/casper_hansen_/status/1875872309996855343

Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025!

[1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)
[2] https://huggingface.co/blog/ganqu/prime

HF Canonical Model Maintainers

AI & ML interests

Recent Activity

hf-maintainers's activity

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

AI & ML interests

Recent Activity

Team members 10

hf-maintainers's activity