โก๏ธ 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.
๐ 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.
๐ง 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! ๐
Introducing ๐ผ๐ฝ๐ฒ๐ป ๐๐ฒ๐ฒ๐ฝ-๐ฅ๐ฒ๐๐ฒ๐ฎ๐ฟ๐ฐ๐ต by Hugging Face! ๐ฅ
OpenAI's latest agentic app Deep Research seems really good... But it's closed, as usual.
โฑ๏ธ So with a team of cracked colleagues, we set ourselves a 24hours deadline to replicate and open-source Deep Research! โฑ๏ธ
โก๏ธ We built open-Deep-Research, an entirely open agent that can: navigate the web autonomously, scroll and search through pages, download and manipulate files, run calculation on data...
We aimed for the best performance: are the agent's answers really rigorous?
On GAIA benchmark, Deep Research had 67% accuracy on the validation set. โก๏ธ open Deep Research is at 55% (powered by o1), it is: - the best pass@1 solution submitted - the best open solution ๐ช๐ช
And it's only getting started ! Please jump in, drop PRs, and let's bring it to the top !
If you are using AWS, give a read. It is a running document to showcase how to deploy and fine-tune DeepSeek R1 models with Hugging Face on AWS.
We're working hard to enable all the scenarios, whether you want to deploy to Inference Endpoints, Sagemaker or EC2; with GPUs or with Trainium & Inferentia.
We have full support for the distilled models, DeepSeek-R1 support is coming soon!! I'll keep you posted.
Now you can launch a code agent directly from your terminal! โจ ๐๐๐๐๐๐๐๐๐ "๐๐๐๐ ๐๐๐๐" directly launches a CodeAgent โถ๏ธ This also works with web agents (replace ๐๐๐๐๐๐๐๐๐ with ๐ ๐๐๐๐๐๐๐) thanks to @merve !
๐พ Another treat from smolagents release 1.7.0: Now agents have a memory mechanism, enabling many possibilities like replaying the last run with ๐๐๐๐๐.๐๐๐๐๐๐ข(), thank you @clefourrier !
โ Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI.
Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo)
Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses.
๐ธ Also, PRO users get 2$ inference credits per month!
Multimodal ๐ฌ - We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG ๐ - UI-TARS are new models by ByteDance to unlock agentic GUI control ๐คฏ 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 ๐ - DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! ๐คฏ - 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 ๐ฃ๏ธ - 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 โฏ๏ธ - 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
Today we make the biggest release in smolagents so far: ๐๐ฒ ๐ฒ๐ป๐ฎ๐ฏ๐น๐ฒ ๐๐ถ๐๐ถ๐ผ๐ป ๐บ๐ผ๐ฑ๐ฒ๐น๐, ๐๐ต๐ถ๐ฐ๐ต ๐ฎ๐น๐น๐ผ๐๐ ๐๐ผ ๐ฏ๐๐ถ๐น๐ฑ ๐ฝ๐ผ๐๐ฒ๐ฟ๐ณ๐๐น ๐๐ฒ๐ฏ ๐ฏ๐ฟ๐ผ๐๐๐ถ๐ป๐ด ๐ฎ๐ด๐ฒ๐ป๐๐! ๐ฅณ
Our agents can now casually open up a web browser, and navigate on it by scrolling, clicking elements on the webpage, going back, just like a user would.
The demo below shows Claude-3.5-Sonnet browsing GitHub for task: "Find how many commits the author of the current top trending repo did over last year." Hi @mlabonne !
Go try it out, it's the most cracked agentic stuff I've seen in a while ๐คฏ (well, along with OpenAI's Operator who beat us by one day)
With the big hype around AI agents these days, I couldnโt 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, boringโฆ
Passionate about outdoors, Iโve always dreamed of a tool that could simplify planning mountain trips while accounting for all potential risks. Thatโs why I built ๐๐น๐ฝ๐ถ๐ป๐ฒ ๐๐ด๐ฒ๐ป๐, a smart assistant designed to help you plan safe and enjoyable itineraries in the French Alps and Pyrenees.
Built using Hugging Face's ๐๐บ๐ผ๐น๐ฎ๐ด๐ฒ๐ป๐๐ library, Alpine Agent combines the power of AI with trusted resources like ๐๐ฌ๐ช๐ต๐ฐ๐ถ๐ณ.๐ง๐ณ (https://skitour.fr/) and METEO FRANCE. Whether itโs 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 projectโfrom defining tools and integrating APIs to selecting the best LLMs like ๐๐ธ๐ฆ๐ฏ2.5-๐๐ฐ๐ฅ๐ฆ๐ณ-32๐-๐๐ฏ๐ด๐ต๐ณ๐ถ๐ค๐ต, ๐๐ญ๐ข๐ฎ๐ข-3.3-70๐-๐๐ฏ๐ด๐ต๐ณ๐ถ๐ค๐ต, or ๐๐๐-4.
โท๏ธ Curious how AI can enhance adventure planning?โจTry the app and share your thoughts: florentgbelidji/alpine-agent ๐ 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!
This work from Chinese startup @MiniMax-AI introduces a novel architecture that achieves state-of-the-art performance while handling context windows up to 4 million tokens - roughly 20x longer than current models. The key was combining lightning attention, mixture of experts (MoE), and a careful hybrid approach.
๐๐ฒ๐ ๐ถ๐ป๐๐ถ๐ด๐ต๐๐:
๐๏ธ MoE with novel hybrid attention: โฃ Mixture of Experts with 456B total parameters (45.9B activated per token) โฃ Combines Lightning attention (linear complexity) for most layers and traditional softmax attention every 8 layers
๐ Outperforms leading models across benchmarks while offering vastly longer context: โฃ Competitive with GPT-4/Claude-3.5-Sonnet on most tasks โฃ Can efficiently handle 4M token contexts (vs 256K for most other LLMs)
๐ฌ Technical innovations enable efficient scaling: โฃ Novel expert parallel and tensor parallel strategies cut communication overhead in half โฃ Improved linear attention sequence parallelism, multi-level padding and other optimizations achieve 75% GPU utilization (that's really high, generally utilization is around 50%)
๐ฏ Thorough training strategy: โฃ Careful data curation and quality control by using a smaller preliminary version of their LLM as a judge!
Overall, not only is the model impressive, but the technical paper is also really interesting! ๐ It has lots of insights including a great comparison showing how a 2B MoE (24B total) far outperforms a 7B model for the same amount of FLOPs.
๐ช๐ฒ'๐๐ฒ ๐ท๐๐๐ ๐ฟ๐ฒ๐น๐ฒ๐ฎ๐๐ฒ๐ฑ ๐๐บ๐ผ๐น๐ฎ๐ด๐ฒ๐ป๐๐ ๐๐ญ.๐ฏ.๐ฌ ๐, and it comes with a major feature: you can now log agent runs using OpenTelemetry to inspect them afterwards! ๐
This interactive format is IMO much easier to inspect big multi-step runs than endless console logs.
The main bottleneck in building GUI agents it to find training data. GUI Agent trajectories are not easy to get by. Crowdsourcing trajectories, then manually annotating them, could be an option, but at scale, it's hard to do
You could use synthetic data generation (ask 1000s small existing GUI agents to solve tasks, keep only successful runs). But then it's hard to come up with many high level-tasks.
โก๏ธ Well, a novel technique was just published that creates a new promising paradigm for synthetic data generation: Shanghai AI Lab researchers propose OS-Genesis, a novel way to create training data for GUI agents that flips the traditional approach on its head. Instead of starting with predefined tasks and having humans or machines execute them, OS-Genesis first explores the interface naturally, then derives meaningful tasks from those interactions.
๐ Exploration-driven vs task-driven approach: โฃ Instead of starting with tasks, OS-Genesis first explores GUIs by clicking and interacting โฃ It then reverse-engineers high-level tasks from successful interaction patterns โฃ This leads to more natural and diverse training data than predefined tasks
๐ฏ Novel reward model for trajectory quality: โฃ Rather than discarding incomplete trajectories, OS-Genesis scores them based on coherence and completion โฃ This preserves valuable partial successes that would otherwise be wasted
๐ Superior results across environments: โฃ Nearly doubles performance on AndroidWorld (9.8% โ 17.4%)
By the way, this field of GUI agents is still in infancy, so you can still make a difference with "low-cost" setups: their paper gets SOTA results with only 8xA100!
Since I published it on GitHub a few days ago, Hugging Face's new agentic library ๐๐บ๐ผ๐น๐ฎ๐ด๐ฒ๐ป๐๐ has gathered nearly 4k stars ๐คฏ
โก๏ธ But we are just getting started on agents: so we are hiring an ML Engineer to join me and double down on this effort!
The plan is to build GUI agents: agents that can act on your computer with mouse & keyboard, like Claude Computer Use.
After 6 years, BERT, the workhorse of encoder models, finally gets a replacement: ๐ช๐ฒ๐น๐ฐ๐ผ๐บ๐ฒ ๐ ๐ผ๐ฑ๐ฒ๐ฟ๐ป๐๐๐ฅ๐ง! ๐ค
We talk a lot about โจGenerative AIโจ, meaning "Decoder version of the Transformers architecture", but this is only one of the ways to build LLMs: encoder models, that turn a sentence in a vector, are maybe even more widely used in industry than generative models.
The workhorse for this category has been BERT since its release in 2018 (that's prehistory for LLMs).
It's not a fancy 100B parameters supermodel (just a few hundred millions), but it's an excellent workhorse, kind of a Honda Civic for LLMs.
Many applications use BERT-family models - the top models in this category cumulate millions of downloads on the Hub.
โก๏ธ Now a collaboration between Answer.AI and LightOn just introduced BERT's replacement: ModernBERT.
๐ง๐;๐๐ฅ: ๐๏ธ Architecture changes: โ First, standard modernizations: - Rotary positional embeddings (RoPE) - Replace GeLU with GeGLU, - Use Flash Attention 2 โจ The team also introduced innovative techniques like alternating attention instead of full attention, and sequence packing to get rid of padding overhead.
๐ฅ As a result, the model tops the game of encoder models: It beats previous standard DeBERTaV3 for 1/5th the memory footprint, and runs 4x faster!
๐ฐ๏ธ Llama-3.1-405B took 39 million GPU-hours to train, i.e. about 4.5 thousand years.
๐ด๐ป If they had needed all this time, we would have GPU stories from the time of Pharaoh ๐: "Alas, Lord of Two Lands, the shipment of counting-stones arriving from Cathay was lost to pirates, this shall delay the building of your computing temple by many moons "
๐ ๏ธ But instead, they just parallelized the training on 24k H100s, which made it take just a few months. This required parallelizing across 4 dimensions: data, tensor, context, pipeline. And it is infamously hard to do, making for bloated code repos that hold together only by magic.
๐ค ๐๐๐ ๐ป๐ผ๐ ๐๐ฒ ๐ฑ๐ผ๐ป'๐ ๐ป๐ฒ๐ฒ๐ฑ ๐ต๐๐ด๐ฒ ๐ฟ๐ฒ๐ฝ๐ผ๐ ๐ฎ๐ป๐๐บ๐ผ๐ฟ๐ฒ! Instead of building mega-training codes, Hugging Face colleagues cooked in the other direction, towards tiny 4D parallelism libs. A team has built Nanotron, already widely used in industry. And now a team releases Picotron, a radical approach to code 4D Parallelism in just a few hundred lines of code, a real engineering prowess, making it much easier to understand what's actually happening!
โก ๐๐'๐ ๐๐ถ๐ป๐, ๐๐ฒ๐ ๐ฝ๐ผ๐๐ฒ๐ฟ๐ณ๐๐น: Counting in MFU (Model FLOPs Utilization, how much the model actually uses all the compute potential), this lib reaches ~50% on SmolLM-1.7B model with 8 H100 GPUs, which is really close to what huge libs would reach. (Caution: the team is leading further benchmarks to verify this)
Current LLMs process text by first splitting it into tokens. They use a module named "tokenizer", that -spl-it-s- th-e- te-xt- in-to- arbitrary tokens depending on a fixed dictionnary. On the Hub you can find this dictionary in a model's files under tokenizer.json.
โก๏ธ This process is called BPE tokenization. It is suboptimal, everyone says it. It breaks text into predefined chunks that often fail to capture the nuance of language. But it has been a necessary evil in language models since their inception.
๐ฅ In Byte Latent Transformer (BLT), Meta researchers propose an elegant solution by eliminating tokenization entirely, working directly with raw bytes while maintaining efficiency through dynamic "patches."
This had been tried before with different byte-level tokenizations, but it's the first time that an architecture of this type scales as well as BPE tokenization. And it could mean a real paradigm shift! ๐๐
๐๏ธ ๐๐ฟ๐ฐ๐ต๐ถ๐๐ฒ๐ฐ๐๐๐ฟ๐ฒ: Instead of a lightweight tokenizer, BLT has a lightweight encoder that process raw bytes into patches. Then the patches are processed by the main heavy-duty transformers as we do normally (but for patches of bytes instead of tokens), before converting back to bytes.
๐งฉ ๐๐๐ป๐ฎ๐บ๐ถ๐ฐ ๐ฃ๐ฎ๐๐ฐ๐ต๐ถ๐ป๐ด: Instead of fixed tokens, BLT groups bytes based on their predictability (measured by entropy) - using more compute for complex sequences and efficiently handling simple ones. This allows efficient processing while maintaining byte-level understanding.
I hope this breakthrough is confirmed and we can get rid of all the tokenizer stuff, it will make model handling easier!
๐ฅ ๐๐ผ๐ผ๐ด๐น๐ฒ ๐ฟ๐ฒ๐น๐ฒ๐ฎ๐๐ฒ๐ ๐๐ฒ๐บ๐ถ๐ป๐ถ ๐ฎ.๐ฌ, ๐๐๐ฎ๐ฟ๐๐ถ๐ป๐ด ๐๐ถ๐๐ต ๐ฎ ๐๐น๐ฎ๐๐ต ๐บ๐ผ๐ฑ๐ฒ๐น ๐๐ต๐ฎ๐ ๐๐๐ฒ๐ฎ๐บ๐ฟ๐ผ๐น๐น๐ ๐๐ฃ๐ง-๐ฐ๐ผ ๐ฎ๐ป๐ฑ ๐๐น๐ฎ๐๐ฑ๐ฒ-๐ฏ.๐ฒ ๐ฆ๐ผ๐ป๐ป๐ฒ๐! And they start a huge effort on agentic capabilities.
๐ The performance improvements are crazy for such a fast model: โฃ Gemini 2.0 Flash outperforms the previous 1.5 Pro model at twice the speed โฃ Now supports both input AND output of images, video, audio and text โฃ Can natively use tools like Google Search and execute code
โก๏ธ If the price is on par with previous Flash iteration ($0.30 / M tokens, to compare with GPT-4o's $1.25) the competition will have a big problem with this 4x cheaper model that gets better benchmarks ๐คฏ
๐ค What about the agentic capabilities?
โฃ Project Astra: A universal AI assistant that can use Google Search, Lens and Maps โฃ Project Mariner: A Chrome extension that can complete complex web tasks (83.5% success rate on WebVoyager benchmark, this is really impressive!) โฃ Jules: An AI coding agent that integrates with GitHub workflows
I'll be eagerly awaiting further news from Google!
๐๐๐๐ฅ๐ข๐ง๐ ๐ฅ๐๐ฐ๐ฌ ๐๐ซ๐ ๐ง๐จ๐ญ ๐๐๐๐ ๐ฒ๐๐ญ! New blog post suggests Anthropic might have an extremely strong Opus-3.5 already available, but is not releasing it to keep their edge over the competition. ๐ง
โSince the release of Opus-3.5 has been delayed indefinitely, there have been lots of rumors and articles about LLMs plateauing. Scaling laws, the main powering factor of the LLM competence increase, could have stopped, according to these rumors, being the cause of this stalling of progress.
These rumors were quickly denied by many people at the leading LLM labs, including OpenAI and Anthropic. But these people would be expected to hype the future of LLMs even if scaling laws really plateaued, so the jury is still out.
๐๏ธ This new article by Semianalysis (generally a good source, specifically on hardware) provides a counter-rumor that I find more convincing:
โก๏ธ Maybe scaling laws still work, Opus-3.5 is ready and as good as planned, but they just don't release it because the synthetic data it helps provide can bring cheaper/smaller models Claude and Haiku up in performance, without risking to leak this precious high-quality synthetic data to competitors.
After some heated discussion ๐ฅ, we clarify our intent re. storage limits on the Hub
TL;DR: - public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible - private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)
We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community ๐ฅ
Last week was crazy in OS AI, with important models and datasets releases every day.
Here are the most important ones I've pinned:
๐ Cohere relased GLobal-MMLU, a multilingual version of MMLU, to evaluate AI models' world knowledge in many languages!
๐ฆ Meta released Llama-3.3-70B-Instruct, a 70B model that's on par with Llama-3.1-405B-Instruct, GPT-4o and Claude. Probably my new go-to for agentic workflows.
๐ FishAudio released fish-speech-1.5, multilingual text to speech model
๐จ Microsoft Research released TRELLIS, an extremely impressive image-to-3D model, which you can try here: JeffreyXiang/TRELLIS
๐ Yesterday, Hugging Face release FineWeb 2, a new version that extends the previous FineWeb to over 1000 languages, including extended coverage in Russina, Mandarin, German, Japanese, Spanish, French, so a huge, high-quality dataset of > 3 trillion words! HuggingFaceFW/fineweb-2
Now let's go build to make this week as productive as last one!
