Just applied for HF Community Grant for “Hugging Research” — a lightweight CodeAgent‑based research assistant built on Hugging Face’s Open Deep Research project for the Hugging Face Hub (models, datasets, Spaces, users, collections, papers). It gathers links via dedicated tools and organizes them for easy review.
As this is for the community, comments and suggestions are appreciated: daqc/hugging-research#1
reacted to dhruv3006's
post with 🔥about 1 month ago
We find that OlympicCoder models outperform Claude 3.7 Sonnet, as well as others over 100x larger 💪
Together with the models, we are releasing:
📊CodeForces-CoTs: new dataset of code problems from the most popular competitive coding platform, with R1 traces in C++ and Python open-r1/codeforces-cots
🏆 IOI'2024: a new benchmark of VERY hard programming problems where even frontier models struggle to match human performance open-r1/ioi
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.
In just 24 hours, we built an open-source agent that: ✅ Autonomously browse the web ✅ Search, scroll & extract info ✅ Download & manipulate files ✅ Run calculations on data
We’re launching a FREE and CERTIFIED course on Agents!
We're thrilled to announce the launch of the Hugging Face Agents course on Learn! This interactive, certified course will guide you through building and deploying your own AI agents.
Here's what you'll learn:
- Understanding Agents: We'll break down the fundamentals of AI agents, showing you how they use LLMs to perceive their environment (observations), reason about it (thoughts), and take actions. Think of a smart assistant that can book appointments, answer emails, or even write code based on your instructions. - Building with Frameworks: You'll dive into popular agent frameworks like LangChain, LlamaIndex and smolagents. These tools provide the building blocks for creating complex agent behaviors. - Real-World Applications: See how agents are used in practice, from automating SQL queries to generating code and summarizing complex documents. - Certification: Earn a certification by completing the course modules, implementing a use case, and passing a benchmark assessment. This proves your skills in building and deploying AI agents. Audience
This course is designed for anyone interested in the future of AI. Whether you're a developer, data scientist, or simply curious about AI, this course will equip you with the knowledge and skills to build your own intelligent agents.
Enroll today and start building the next generation of AI agent applications!
🎯Triangulum is a collection of pretrained and instruction-tuned generative models, designed for multilingual applications. These models are trained using synthetic datasets based on long chains of thought, enabling them to perform complex reasoning tasks effectively.
The Hugging Face Download Tool is a sophisticated graphical user interface application designed to simplify the process of downloading resources from Hugging Face repositories. This tool addresses common challenges in model and file downloads through its intelligent features and user-friendly interface.
✨ Key Features - 🖥️ Intuitive graphical interface for easy operation - 🔄 Advanced retry mechanism with smart error handling - ⏸️ Resume capability for interrupted downloads - 📊 Real-time download status monitoring - 🔐 Secure access to private repositories via token authentication
🛠️ Technical Highlights The tool implements several advanced features to ensure reliable downloads: - 📦 Chunk-based downloading with 1MB segments - ⚡ Adaptive retry intervals (5-300 seconds) based on error types - 🔌 Connection pooling for optimized performance - 🛡️ Built-in rate limiting protection - 🔑 Secure token handling for private repository access
This tool is ideal for researchers, developers, and AI practitioners who regularly work with Hugging Face resources and need a reliable, user-friendly download solution. 💻 It supports all major operating systems and requires minimal setup, making it accessible to users of all technical levels. 🚀
We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute 🔥
How? By combining step-wise reward models with tree search algorithms :)
We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"
We're open sourcing the full recipe and sharing a detailed blog post.
In our blog post we cover:
📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.
🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.
🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM
* Iteratively sample CoTs from the model, using a mix of different search strategies. This gives you something like Stream of Search via prompting. * Verify correctness of each CoT using GPT-4o (needed because exact match doesn't work well in medicine where there are lots of aliases) * Use GPT-4o to reformat the concatenated CoTs into a single stream that includes smooth transitions like "hmm, wait" etc that one sees in o1 * Use the resulting data for SFT & RL * Use sparse rewards from GPT-4o to guide RL training. They find RL gives an average ~3 point boost across medical benchmarks and SFT on this data already gives a strong improvement.
Applying this strategy to other domains could be quite promising, provided the training data can be formulated with verifiable problems!
It's 2025, you shouldn't be hand writing SQL! This is a big step in making it where anyone can do in depth analysis on a dataset. Let us know what you think 🤗
