Loading…
Hugging Face
AI platform and community providing machine learning models, datasets, libraries, and tools for building AI applications.
- 317 posts summarised
- latest
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
From their blog
Latest articles
Large Language Models: A New Moore's Law?
Recent advancements in generative artificial intelligence have spurred the rapid growth of large language models like Megatron-Turing NLG 530B, which require vast financial investments and substantial energy consumption. Training these massive parameter architectures demands hundreds of multi-GPU servers and generates significant carbon footprints for relatively modest benchmark gains. Rather than relying on brute-force scaling, engineering teams can adopt smaller, more frugal architectures through knowledge distillation and transfer learning techniques. Practical alternatives include fine-tuning existing pretrained models, deploying on energy-efficient cloud infrastructure, and applying optimizations like pruning, layer fusion, and quantization. These methods deliver low-latency inference and high task accuracy while significantly decreasing hardware requirements, development time, and environmental impact.
Train a Sentence Embedding Model with 1B Training Pairs
Sentence embeddings map sentences into dense vectors to capture semantic meaning for downstream tasks such as clustering, asymmetric question answering, and text search. To train general-purpose models at scale, the team utilized a dataset compiled from multiple sources containing up to one billion sentence pairs. Training leveraged contrastive learning with Multiple Negative Ranking Loss and in-batch negatives, running across seven TPU v3-8 accelerators with JAX and Flax. Batches combined samples from at least two datasets to balance hard negatives within topics against broader cross-topic semantic structure. The project resulted in twenty trained models—including variants of RoBERTa, DistilBERT, and MPNet—alongside eight specialized evaluation datasets and an interactive demo covering sentence similarity, search, and gender bias.
The Age of Machine Learning As Code Has Arrived
Recent findings from the 2021 State of AI Report and Kaggle State of Machine Learning and Data Science Survey indicate that machine learning is expanding into critical infrastructure while Transformers become general-purpose architectures across text, vision, and audio. In response, organizations face questions about scaling infrastructure, team composition, and engineering maturity. Rather than treating machine learning as isolated sandbox experiments or hiring solely data scientists, teams benefit from adopting established software engineering and DevOps principles like versioning, testing, automation, and continuous deployment. Furthermore, the rise of pre-trained Transformer architectures enables practitioners to fine-tune existing off-the-shelf models rather than training from scratch, reducing compute costs and training duration. Tools from platforms such as Hugging Face streamline model deployment, latency optimization, and infrastructure abstraction.
Fine tuning CLIP with Remote Sensing (Satellite) images and captions
Pre-trained vision-language models like CLIP generalize well across everyday imagery but struggle with remote sensing domain characteristics. To enable text-based search across satellite imagery, a distributed team fine-tuned the openai/clip-vit-base-patch32 model on TPU hardware using JAX and Flax during the Hugging Face Flax/JAX Community Week. The training pipeline incorporated satellite image and caption pairs from the RSICD, UCM, and Sydney datasets alongside extensive image transforms and backtranslation-based text augmentation. Contrastive optimization using Adam with a learning rate of 5e-6 achieved top-1 retrieval accuracy of 0.883 compared to 0.572 on the baseline model. An interactive demo uses a NMSLib index for text-to-image matching, image-to-image matching, and patch-level feature detection.
Hosting your Models and Datasets on Hugging Face Spaces using Streamlit
Streamlit enables developers to create interactive web demonstrations and visualizations for machine learning models and datasets. In an illustrative text completion interface recreating Write with Transformer, UI components such as text areas, sidebars, number inputs, and continuous sliders collect user text and inference hyperparameters. For data inspection, the streaming feature in Hugging Face Datasets loads large corpora directly into memory without requiring complete local downloads, integrating with pandas, matplotlib, and seaborn for tabular and chart rendering. Deploying these interactive applications to Hugging Face Spaces involves uploading the code files while defining dependencies inside a requirements.txt file. Matching local Streamlit versions ensures consistent runtime execution when hosting models and datasets online.
Showcase Your Projects in Spaces using Gradio
Demonstrating machine learning projects to the community requires accessible hosting and minimal interface boilerplate. Gradio integrates directly with the Hugging Face Hub and its underlying Inference API, enabling developers to load models using repository identifiers and launch interactive interfaces with a few lines of code. Hugging Face Spaces provides a free hosting environment where users select Gradio as the SDK, commit an app.py script, and deploy live web demonstrations for frameworks like Transformers, spaCy, SpeechBrain, and Asteroid. For complex workflows, developers can chain multiple models sequentially via Gradio Series or host custom checkpoints directly when models lack native Inference API support.
Summer at Hugging Face
Hugging Face released several major updates across its ecosystem, expanding its public Hub repository to over 16,000 models. Platform additions include Spaces for deploying Gradio and Streamlit demo applications, automatic TensorBoard instances, and evaluation metric tracking integrated with Papers With Code leaderboards. The Transformers library gained JAX/Flax support across more than 5,000 models, improved TensorFlow implementations, and introduced the transformers.onnx export module for model conversion. In research, the BigScience project completed large-scale training of a 13-billion-parameter English decoder model on Jean Zay, while the DeDLOC method enabled training the sahajBERT Bengali model without HPC infrastructure. Accepted conference papers detailed the Datasets library, prompt data-point equivalence, prompt-based fine-tuning heuristics, and block pruning techniques that reduced BERT size by 74 percent.
Hugging Face and Graphcore partner for IPU-optimized Transformers
Hugging Face launched its Hardware Partner Program at the 2021 AI Hardware Summit to offer device-optimized models and software integrations. As a founding member of the program, Graphcore collaborated with Hugging Face to optimize Transformer models for its Intelligence Processing Unit (IPU). Graphcore IPUs use a massively parallel MIMD architecture with on-die ultra-high bandwidth memory designed for AI workloads featuring fine-grained parallelism, low precision arithmetic, and sparsity. Through Hugging Face's open-source Optimum toolkit, developers will receive plug-and-play access to certified, hardware-optimized models across vision, speech, translation, and text generation. Graphcore's Poplar SDK integrates with PyTorch, TensorFlow, Docker, and Kubernetes, simplifying the process of porting workloads to IPU-POD datacenter compute systems.
Introducing Optimum: The Optimization Toolkit for Transformers at Scale
Running Transformer models fast and efficiently at production scale presents a significant challenge due to the complex compatibility between model architectures, acceleration techniques like quantization or sparsity, and specific silicon hardware features. Hugging Face introduced Optimum, an open-source library built to abstract hardware acceleration complexity and optimize training and inference on target devices through direct collaborations with hardware partners. Using quantization as a primary example, engineering teams often struggle with eager-mode model graph modifications, kernel compatibility checks, calibration parameter tuning, and acceptable accuracy loss trade-offs. Optimum addresses these challenges by integrating tools such as Intel Neural Compressor, which supports post-training quantization, quantization-aware training, and dynamic quantization driven by user-defined YAML configurations. Through these hardware-tailored integrations, the library aims to democratize production performance and reduce the aggregate energy consumed by machine learning workloads.
Deep Learning over the Internet: Training Language Models Collaboratively
Pretraining state-of-the-art Transformer language models typically requires vast computing resources and expensive hardware clusters that are inaccessible to many researchers. Standard distributed deep learning struggles over public Internet infrastructure because consumer connections suffer from limited bandwidth, dynamic peer disconnections, and restrictive firewalls. To resolve these networking bottlenecks, Distributed Deep Learning in Open Collaborations (DeDLOC) introduces an adaptive training framework that accumulates massive batch sizes across heterogeneous volunteer devices before applying optimizer updates. The framework splits gradient vectors dynamically based on participant connection speeds and allows firewalled nodes to contribute data without performing aggregation. In a practical deployment with 40 volunteers, the 18-million-parameter sahajBERT model achieved Bengali downstream benchmark performance comparable to much larger multilingual models trained on dedicated supercomputers.
Welcome spaCy to the Hugging Face Hub
Hugging Face has integrated spaCy pipelines into the Hugging Face Hub to simplify the distribution, testing, and deployment of natural language processing models across the community. More than 60 canonical models from the spaCy 3.1 release are hosted in the spaCy organization, alongside discoverable community pipelines. Users can package and upload models directly through the command line using the spacy-huggingface-hub extension, which auto-generates required metadata and model cards. Hosted pipelines offer direct pip installation from live wheel URLs, interactive browser exploration, and production-ready HTTP endpoints through the Inference API. The platform provides immediate interactive widget support for named entity recognition components, with upcoming support planned for text classification and part-of-speech tagging pipelines.
Deploy Hugging Face models easily with Amazon SageMaker
Hugging Face and Amazon introduced an inference solution integrating Hugging Face Transformers with Amazon SageMaker. The SageMaker Hugging Face Inference Toolkit and specialized Deep Learning Containers enable deployment of trained models or publicly available Hub models to managed production endpoints. Users configure endpoints with minimal code using the SageMaker Python SDK, standard pipelines, or custom inference scripts that override default behaviors. The architecture supports models stored in Amazon S3 as well as direct references via HF_MODEL_ID and HF_TASK environment variables. Deployments benefit from native AWS infrastructure features, including built-in monitoring, Identity and Access Management permission controls, and Virtual Private Cloud connectivity.
Sentence Transformers in the Hugging Face Hub
Sentence Transformers has collaborated with the Hugging Face Hub as part of its v2 release to make sentence, paragraph, and image embedding models readily accessible. The Hub now hosts over 90 pretrained models supporting more than 100 languages for use cases like semantic search and multilingual zero-shot classification. Alongside direct model loading in minimal code, the platform provides interactive Hub widgets for feature extraction and sentence similarity computation. Developers can execute inference programmatically through Inference API endpoints. Additionally, the library supports direct model uploading to the Hub via save_to_hub, which automatically generates a model card detailing layer architecture and dual usage with Sentence Transformers and Transformers.
Few-shot learning in practice: GPT-Neo and the 🤗 Accelerated Inference API
Limited labeled data often prevents machine learning models from achieving high performance during traditional fine-tuning. Few-shot learning addresses this hurdle in natural language processing by supplying a short task description and a few demonstration examples at inference time. EleutherAI developed GPT-Neo, an open transformer-based model trained on the Pile dataset, which can execute few-shot tasks via the Hugging Face Accelerated Inference API. Compared to larger models like GPT-3, the 2.7B parameter version of GPT-Neo requires three to four examples alongside tuned hyperparameters like temperature and stopping sequences to generate accurate completions. Because few-shot learning relies heavily on pre-trained associations, careful output monitoring and human feedback mechanisms remain necessary to prevent automated bias.
Using & Mixing Hugging Face Models with Gradio 2.0
The Hugging Face Model Hub hosts more than 10,000 user-submitted machine learning models spanning natural language processing, image classification, and audio processing. Machine learning developers increasingly need to demo models to interdisciplinary collaborators or non-programmers to uncover biases and failure points. The Gradio 2.0 library enables users to create graphical user interfaces and load almost any Hugging Face model using a single line of code. By default, these interfaces query Hugging Face's hosted Inference API without requiring an API key, though users can also run computations locally via the transformers library. Gradio interfaces can be customized through the Interface class and composed to load multiple models in parallel or chain them in series.
Scaling-up BERT Inference on CPU (Part 1)
Scaling BERT-like model inference on CPUs presents practical deployment challenges as transformer architectures proliferate in production environments. Using a reproducible Hydra-based benchmarking framework, inference workloads were evaluated on an Amazon Web Services c5.metal instance featuring an Intel Xeon Platinum 8275 processor with AVX512 and VNNI support. Out-of-the-box evaluations showed PyTorch 1.8.1 delivering lower latency than Google TensorFlow 2.4.0, likely due to PyTorch relying on OpenMP and Intel MKL/oneDNN rather than Eigen. Implementing multiple inference streams by pinning parallel model instances to dedicated CPU cores yielded near-linear throughput scaling. Matching instance core allocations to specific problem sizes also demonstrated that smaller workloads can achieve optimal latency on fewer cores, enabling up to a sixfold reduction in cloud compute costs.
Introducing 🤗 Accelerate
🤗 Accelerate enables PyTorch developers to execute raw training loops across CPUs, multi-GPU setups, and TPUs with minimal boilerplate modifications. Standard distributed training typically demands manual device assignments, DistributedSampler configurations, and divergent code paths that break single-device portability. By wrapping models, optimizers, and dataloaders through a unified prepare call, Accelerate automatically manages hardware placement, mixed precision operations, and sampler batch slicing without requiring custom distributed samplers. Distributed evaluation is streamlined using a gather utility that consolidates prediction tensors across active worker processes. Furthermore, a dedicated command-line interface provides an interactive questionnaire to store runtime configuration defaults and orchestrate local or AWS SageMaker runs.
Distributed Training: Train BART/T5 for Summarization using 🤗 Transformers and Amazon SageMaker
Hugging Face and Amazon SageMaker introduced optimized Deep Learning Containers alongside a SageMaker Python SDK estimator to streamline distributed transformer model training. This workflow demonstrates fine-tuning the 400-million-parameter facebook/bart-large-cnn model for dialogue summarization on the 16,000-conversation samsum dataset. Using SageMaker Data Parallelism enabled in the distribution configuration, training executes across two ml.p3dn.24xlarge compute instances equipped with sixteen total GPUs and a cumulative batch size of 64. The HuggingFace estimator pulls the run_summarization.py script directly from GitHub, enables mixed precision with fp16, and tracks evaluation performance through ROUGE scores. Following completion, the unzipped model artifacts and a generated model card are pushed to the Hugging Face Hub using the huggingface_hub library for hosted inference.
Understanding BigBird's Block Sparse Attention
Transformer-based models face severe computational bottlenecks due to quadratic time and memory complexity, making sequences longer than 512 tokens impractical. BigBird addresses this limitation by approximating full attention with block sparse attention, scaling context lengths up to 4096 tokens at a lower computational cost. Instead of attending to all tokens, BigBird combines sliding attention for local context, global tokens for long-range relationships, and random tokens to accelerate information transfer. The model is integrated into HuggingFace Transformers, enabling fine-tuning for tasks like long-document summarization and extractive question answering. When sequences are shorter than 1024 tokens, using original full attention remains recommended.
The Partnership: Amazon SageMaker and Hugging Face
Hugging Face and Amazon formed a strategic partnership establishing Amazon Web Services as Hugging Face's preferred cloud provider to simplify training and deploying Transformer models. To facilitate this collaboration, the teams introduced Hugging Face Deep Learning Containers optimized for PyTorch and TensorFlow in Amazon SageMaker. The integration provides an extension to the SageMaker Python SDK, enabling data science teams to configure distributed training jobs across single-node and multi-node GPU clusters. Workflows integrate directly with SageMaker Automatic Model Tuning, SageMaker Studio, and Amazon S3 for managed experiment tracking and artifact storage. The open-source containers allow trained models to be exported for inference via SageMaker or published directly to the Hugging Face Model Hub while utilizing EC2 Spot instances to reduce compute expenses.
Topics they write about
All topics →Weekly digest
The best engineering reads, once a week.