HuggingFaceM4 (HuggingFaceM4)

lysandre

posted an update about 2 hours ago

Post

159

SmolVLM-2 and SigLIP-2 are now part of 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

·

davanstrien

posted an update about 22 hours ago

Post

1384

Hacked together a way to log trl GRPO training completions to a 🤗 dataset repo. This allows you to:

- Track rewards from multiple reward functions
- Treat the completion and rewards from training as a "proper" dataset and do EDA
- Share results for open science

The implementation is super hacky, but I'm curious if people would find this useful.

To push completions to the Hub, you just need two extra parameters:

log_completions=True
log_completions_hub_repo='your-username/repo-name'

Example dataset: davanstrien/test-logs
Colab: https://colab.research.google.com/drive/1wzBFPVthRYYTp-mEYlznLg_e_0Za1M3g

frimelle

authored 2 papers 1 day ago

Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions

Paper • 2310.05779 • Published Oct 9, 2023 • 1

Presumed Cultural Identity: How Names Shape LLM Responses

Paper • 2502.11995 • Published 4 days ago • 9

frimelle

posted an update 1 day ago

Post

1490

What’s in a name? More than you might think, especially for AI.
Whenever I introduce myself, people often start speaking French to me, even though my French is très basic. It turns out that AI systems do something similar:
Large language models infer cultural identity from names, shaping their responses based on presumed backgrounds. But is this helpful personalization or a reinforcement of stereotypes?
In our latest paper, we explored this question by testing DeepSeek, Llama, Aya, Mistral-Nemo, and GPT-4o-mini on how they associate names with cultural identities. We analysed 900 names from 30 cultures and found strong assumptions baked into AI responses: some cultures were overrepresented, while others barely registered.
For example, a name like "Jun" often triggered Japan-related responses, while "Carlos" was linked primarily to Mexico, even though these names exist in multiple countries. Meanwhile, names from places like Ireland led to more generic answers, suggesting weaker associations in the training data.
This has real implications for AI fairness: How should AI systems personalize without stereotyping? Should they adapt at all based on a name?
Work with some of my favourite researchers: @sidicity Arnav Arora and @IAugenstein
Read the full paper here: Presumed Cultural Identity: How Names Shape LLM Responses (2502.11995)

merve

posted an update 2 days ago

Post

3717

Google just released PaliGemma 2 Mix: new versatile instruction vision language models 🔥

> Three new models: 3B, 10B, 28B with res 224, 448 💙
> Can do vision language tasks with open-ended prompts, understand documents, and segment or detect anything 🤯

Read more https://huggingface.co/blog/paligemma2mix
Try the demo google/paligemma2-10b-mix
All models are here google/paligemma-2-mix-67ac6a251aaf3ee73679dcc4

clem

posted an update 3 days ago

Post

2491

1 reply

·

m-ric

posted an update 3 days ago

Post

2342

Less is More for Reasoning (LIMO): a 32B model fine-tuned with 817 examples can beat o1-preview on math reasoning! 🤯

Do we really need o1's huge RL procedure to see reasoning emerge? It seems not.
Researchers from Shanghai Jiaotong University just demonstrated that carefully selected examples can boost math performance in large language models using SFT —no huge datasets or RL procedures needed.

Their procedure allows Qwen2.5-32B-Instruct to jump from 6.5% to 57% on AIME and from 59% to 95% on MATH, while using only 1% of the data in previous approaches.

⚡ The Less-is-More Reasoning Hypothesis:
‣ Minimal but precise examples that showcase optimal reasoning patterns matter more than sheer quantity
‣ Pre-training knowledge plus sufficient computational resources at inference levels up math skills

➡️ Core techniques:
‣ High-quality reasoning chains with self-verification steps
‣ 817 handpicked problems that encourage deeper reasoning
‣ Enough inference-time computation to allow extended reasoning

💪 Efficiency gains:
‣ Only 817 examples instead of 100k+
‣ 40.5% absolute improvement across 10 diverse benchmarks, outperforming models trained on 100x more data

This really challenges the notion that SFT leads to memorization rather than generalization! And opens up reasoning to GPU-poor researchers 🚀

Read the full paper here 👉 LIMO: Less is More for Reasoning (2502.03387)

clem

posted an update 4 days ago

Post

3252

We crossed 1B+ tokens routed to inference providers partners on HF, that we released just a few days ago.

Just getting started of course but early users seem to like it & always happy to be able to partner with cool startups in the ecosystem.

Have you been using any integration and how can we make it better?

https://huggingface.co/blog/inference-providers

davanstrien

posted an update 5 days ago

Post

2149

Dataset descriptions for trending Hugging Face datasets? Powered by a Smol model davanstrien/Smol-Hub-tldr

merve

posted an update 7 days ago

Post

4569

Your weekly recap of open AI is here, and it's packed with models! merve/feb-14-releases-67af876b404cc27c6d837767

👀 Multimodal
> OpenGVLab released InternVideo 2.5 Chat models, new video LMs with long context
> AIDC released Ovis2 model family along with Ovis dataset, new vision LMs in different sizes (1B, 2B, 4B, 8B, 16B, 34B), with video and OCR support
> ColQwenStella-2b is a multilingual visual retrieval model that is sota in it's size
> Hoags-2B-Exp is a new multilingual vision LM with contextual reasoning, long context video understanding

💬 LLMs
A lot of math models!
> Open-R1 team released OpenR1-Math-220k large scale math reasoning dataset, along with Qwen2.5-220K-Math fine-tuned on the dataset, OpenR1-Qwen-7B
> Nomic AI released new Nomic Embed multilingual retrieval model, a MoE with 500 params with 305M active params, outperforming other models
> DeepScaleR-1.5B-Preview is a new DeepSeek-R1-Distill fine-tune using distributed RL on math
> LIMO is a new fine-tune of Qwen2.5-32B-Instruct on Math

🗣️ Audio
> Zonos-v0.1 is a new family of speech recognition models, which contains the model itself and embeddings

🖼️ Vision and Image Generation
> We have ported DepthPro of Apple to transformers for your convenience!
> illustrious-xl-v1.0 is a new illustration generation model

3 replies

·

davanstrien

posted an update 7 days ago

Post

1824

How do you make 1M+ Hugging Face models & datasets more discoverable?

davanstrien/Smol-Hub-tldr!

I fine-tuned HuggingFaceTB/SmolLM2-360M to generate one-line summaries from a model or dataset README.

Its own self-description?
"A model for generating concise summaries of model & dataset cards from the Hugging Face Hub"

The goal? Make it easier to find the right models and datasets for your specific needs. It's already powering a semantic search for datasets Space.

It's still a WIP but thanks to @loubnabnl , @anton-l , @eliebak et al, for cooking such a nice base model for fine-tuning small, efficient models for specific domains and tasks. 🙏

m-ric

posted an update 7 days ago

Post

2627

𝗚𝗿𝗲𝗮𝘁 𝗳𝗲𝗮𝘁𝘂𝗿𝗲 𝗮𝗹𝗲𝗿𝘁: you can now share agents to the Hub! 🥳🥳

And any agent pushed to Hub get a cool Space interface to directly chat with it.

This was a real technical challenge: for instance, serializing tools to export them meant that you needed to get all the source code for a tool, verify that it was standalone (not relying on external variables), and gathering all the packages required to make it run.

Go try it out! 👉 https://github.com/huggingface/smolagents

2 replies

·

m-ric

posted an update 7 days ago

Post

2322

For those who haven't come across it yet, here's a handy trick to discuss an entire GitHub repo with an LLM:

=> Just replace "github" with "gitingest" in the url, and you get the whole repo as a single string that you can then paste in your LLMs

davanstrien

posted an update 8 days ago

Post

1299

Made some significant updates to my 🤗 semantic datasets search app. If you love falling into a wiki black hole, you might like this...

librarian-bots/huggingface-datasets-semantic-search

m-ric

posted an update 9 days ago

Post

4672

"𝟮𝟬𝟮𝟱 𝘄𝗶𝗹𝗹 𝗯𝗲 𝘁𝗵𝗲 𝘆𝗲𝗮𝗿 𝗼𝗳 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀": this statement has often been made, here are numbers to support it.

I've plotted the progress of AI agents on GAIA test set, and it seems they're headed to catch up with the human baseline in early 2026.

And that progress is still driven mostly by the improvement of base LLMs: progress would be even faster with fine-tuned agentic models.

lewtun

posted an update 11 days ago

Post

4437

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

giadap

authored a paper 11 days ago

Fully Autonomous AI Agents Should Not be Developed

Paper • 2502.02649 • Published 17 days ago • 23

merve

posted an update 14 days ago

Post

3021

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

m-ric

posted an update 14 days ago

Post

3633

𝗔𝗱𝘆𝗲𝗻'𝘀 𝗻𝗲𝘄 𝗗𝗮𝘁𝗮 𝗔𝗴𝗲𝗻𝘁𝘀 𝗕𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸 𝘀𝗵𝗼𝘄𝘀 𝘁𝗵𝗮𝘁 𝗗𝗲𝗲𝗽𝗦𝗲𝗲𝗸-𝗥𝟭 𝘀𝘁𝗿𝘂𝗴𝗴𝗹𝗲𝘀 𝗼𝗻 𝗱𝗮𝘁𝗮 𝘀𝗰𝗶𝗲𝗻𝗰𝗲 𝘁𝗮𝘀𝗸𝘀! ❌

➡️ How well do reasoning models perform on agentic tasks? Until now, all indicators seemed to show that they worked really well. On our recent reproduction of Deep Search, OpenAI's o1 was by far the best model to power an agentic system.

So when our partner Adyen built a huge benchmark of 450 data science tasks, and built data agents with smolagents to test different models, I expected reasoning models like o1 or DeepSeek-R1 to destroy the tasks at hand.

👎 But they really missed the mark. DeepSeek-R1 only got 1 or 2 out of 10 questions correct. Similarly, o1 was only at ~13% correct answers.

🧐 These results really surprised us. We thoroughly checked them, we even thought our APIs for DeepSeek were broken and colleagues Leandro Anton helped me start custom instances of R1 on our own H100s to make sure it worked well.
But there seemed to be no mistake. Reasoning LLMs actually did not seem that smart. Often, these models made basic mistakes, like forgetting the content of a folder that they had just explored, misspelling file names, or hallucinating data. Even though they do great at exploring webpages through several steps, the same level of multi-step planning seemed much harder to achieve when reasoning over files and data.

It seems like there's still lots of work to do in the Agents x Data space. Congrats to Adyen for this great benchmark, looking forward to see people proposing better agents! 🚀

Read more in the blog post 👉 https://huggingface.co/blog/dabstep

HuggingFaceM4

AI & ML interests

Recent Activity

HuggingFaceM4's activity

Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions

Presumed Cultural Identity: How Names Shape LLM Responses

Fully Autonomous AI Agents Should Not be Developed

AI & ML interests

Recent Activity

Team members 43

HuggingFaceM4's activity