Hugging Face Unveils Microduck: A $399 Open-Source 25 cm Biped You Train with Reinforcement LearningMichal Sutter writes about Pollen Robotics, a Bordeaux-based team at Hugging Face, which has opened pre-orders for Microduck, a 25 cm bipedal robot priced at $399. Unlike most robotics launches that rely on demo videos, Microduck ships with its full training loop — every movement (walking, sitting, kicking, roller-skating, self-recovery) is a neural policy trained in a physics simulator and exported to hardware. The robot carries 15 motors, a camera, LiDAR, two IMUs, and a Rockchip RK3566, with policies trained via PPO in MuJoCo Warp in roughly one to two hours on a CUDA GPU.
- Sim-to-real hinges on a BAM actuator model (voltage control law, back-EMF, Coulomb/Stribeck/load-dependent friction) plus randomization of battery voltage, command delay, and ±1° backlash per joint
- Every policy shares a 61-dimensional actor observation (48 proprioception + twist, head pose, body pose commands), enabling hot-swap between walk, recover, and trick policies mid-run
- Software is Apache-2.0, but mechanical and electronic design files are not open
- The robot generates a unique audio identity on first wake that persists permanently; it does not speak in a linguistic sense
- Pre-orders opened August 27, 2026, with deliveries targeted before Christmas
- Sim-to-real hinges on a BAM actuator model (voltage control law, back-EMF, Coulomb/Stribeck/load-dependent friction) plus randomization of battery voltage, command delay, and ±1° backlash per joint
- Every policy shares a 61-dimensional actor observation (48 proprioception + twist, head pose, body pose commands), enabling hot-swap between walk, recover, and trick policies mid-run
- Software is Apache-2.0, but mechanical and electronic design files are not open
- The robot generates a unique audio identity on first wake that persists permanently; it does not speak in a linguistic sense
- Pre-orders opened August 27, 2026, with deliveries targeted before Christmas
Learn how to label text without the need for task-specific training data by using zero-shot text classification. This guide explains how pretrained transformer models, such as BART, reframe classification as a reasoning task where labels are treated as natural language statements.
Key topics include:
* The core concept of zero-shot classification and its advantages for rapid prototyping.
* Using the Hugging Face transformers pipeline with the facebook/bart-large-mnli model.
* Implementing multi-label classification for texts belonging to multiple categories.
* Improving accuracy through custom hypothesis template tuning and clear label wording.
Key topics include:
* The core concept of zero-shot classification and its advantages for rapid prototyping.
* Using the Hugging Face transformers pipeline with the facebook/bart-large-mnli model.
* Implementing multi-label classification for texts belonging to multiple categories.
* Improving accuracy through custom hypothesis template tuning and clear label wording.
This page showcases the diverse collection of machine learning models and datasets provided by Arcee AI on Hugging Face. The collections include the advanced Trinity family of models, such as Trinity-Large-Thinking and Trinity-Mini, designed for various text generation tasks. Additionally, the repository features specialized datasets like Teacher Logits for distillation, the AFM 4.5B series, and various quantized flagship models like Virtuoso and SuperNova. These resources cater to researchers and developers looking for high-performance, specialized AI models ranging from small-scale nano versions to massive 399B parameter models, supporting tasks like feature extraction and text generation.
This page details the command-line utility for the Embedding Atlas, a tool for exploring large text datasets with metadata. It covers installation, data loading (local and Hugging Face), visualization of embeddings using SentenceTransformers and UMAP, and usage instructions with available options.
This Space demonstrates a simple method for embedding text using a LLM (Large Language Model) via the Hugging Face Inference API. It showcases how to convert text into numerical vector representations, useful for semantic search and similarity comparisons.
This tutorial demonstrates how to build a powerful document search engine using Hugging Face embeddings, Chroma DB, and Langchain for semantic search capabilities.
Hugging Face researchers developed an open-source AI research agent called 'Open Deep Research' in 24 hours, aiming to match OpenAI's Deep Research. The project demonstrates the potential of agent frameworks to enhance AI model capabilities, achieving 55.15% accuracy on the GAIA benchmark. The initiative highlights the rapid development and collaborative nature of open-source AI projects.
Hugging Face's initiative to replicate DeepSeek-R1, focusing on developing datasets and sharing training pipelines for reasoning models.
The article introduces Hugging Face's Open-R1 project, a community-driven initiative to reconstruct and expand upon DeepSeek-R1, a cutting-edge reasoning language model. DeepSeek-R1, which emerged as a significant breakthrough, utilizes pure reinforcement learning to enhance a base model's reasoning capabilities without human supervision. However, DeepSeek did not release the datasets, training code, or detailed hyperparameters used to create the model, leaving key aspects of its development opaque.
The Open-R1 project aims to address these gaps by systematically replicating and improving upon DeepSeek-R1's methodology. The initiative involves three main steps:
1. **Replicating the Reasoning Dataset**: Creating a reasoning dataset by distilling knowledge from DeepSeek-R1.
2. **Reconstructing the Reinforcement Learning Pipeline**: Developing a pure RL pipeline, including large-scale datasets for math, reasoning, and coding.
3. **Demonstrating Multi-Stage Training**: Showing how to transition from a base model to supervised fine-tuning (SFT) and then to RL, providing a comprehensive training framework.
The article introduces Hugging Face's Open-R1 project, a community-driven initiative to reconstruct and expand upon DeepSeek-R1, a cutting-edge reasoning language model. DeepSeek-R1, which emerged as a significant breakthrough, utilizes pure reinforcement learning to enhance a base model's reasoning capabilities without human supervision. However, DeepSeek did not release the datasets, training code, or detailed hyperparameters used to create the model, leaving key aspects of its development opaque.
The Open-R1 project aims to address these gaps by systematically replicating and improving upon DeepSeek-R1's methodology. The initiative involves three main steps:
1. **Replicating the Reasoning Dataset**: Creating a reasoning dataset by distilling knowledge from DeepSeek-R1.
2. **Reconstructing the Reinforcement Learning Pipeline**: Developing a pure RL pipeline, including large-scale datasets for math, reasoning, and coding.
3. **Demonstrating Multi-Stage Training**: Showing how to transition from a base model to supervised fine-tuning (SFT) and then to RL, providing a comprehensive training framework.
A detailed guide on creating a text classification model with Hugging Face's transformer models, including setup, training, and evaluation steps.
HunyuanVideo is an open-source video generation model that showcases performance comparable to or superior to leading closed-source models. It includes features like a unified image and video generative architecture, a large language model text encoder, and a causal 3D VAE for spatial-temporal compression.
