1sec.ai

Tag

#hugging-face

Every item tagged hugging-face, newest first.

50 items

tools1d

Agentic Resource Discovery: Let agents search

Hugging Face has launched Agentic Resource Discovery, a feature that enables agents to search for and access resources on the platform. This allows builders to integrate agent capabilities into their applications, leveraging Hugging Face's repository of models and datasets. The feature aims to streamline the process of finding and utilizing resources, making it easier for developers to build and deploy AI-powered applications. You can now use agents to discover and access resources on Hugging 

Key takeaways
  • Agentic Resource Discovery is now available on Hugging Face.
  • Enables agents to search and access platform resources.
  • Streamlines resource discovery for AI application development.
HHugging Face Blog#agent-search#hugging-face
models1d

Source code for LLMs. [D]

The source code for several open-source LLMs, including GPT-OSS, appears to be available in Hugging Face's Transformers repository. The code includes full implementations for some models, while others may be skeletons for experimentation. You can find the code for GPT-OSS and other models in the repository's models directory. This code availability can help builders understand and build upon existing LLM architectures.

Key takeaways
  • GPT-OSS implementation appears to be fully available.
  • Other models in the repo may be skeletons for experimentation.
  • Code is in Hugging Face's Transformers repository.
rr/MachineLearning#open-source#llm-code#hugging-face
modelsJun 9

How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces

A developer created a 3D Paris gallery by chaining two Hugging Face Spaces, demonstrating an agent that can combine existing tools to build new applications. The agent used a text-to-image model and a 3D rendering service to generate the gallery. This approach shows builders how to leverage existing services to create complex applications with minimal development effort. The example highlights the potential for agents to simplify development workflows.

Key takeaways
  • Agent combined two Hugging Face Spaces to build a 3D gallery.
  • Used text-to-image and 3D rendering services.
  • Demonstrates potential for agents to simplify development workflows.
HHugging Face Blog#hugging-face#agent#3d-rendering#text-to-image
toolsJun 9

Migrating Your GitHub CI to Hugging Face Jobs

GitHub CI can be migrated to Hugging Face Jobs, providing a seamless integration with Hugging Face's infrastructure. This allows for efficient management of machine learning workflows. You can leverage Hugging Face's scalable compute resources and integrate with existing GitHub repositories. The migration process is straightforward, enabling you to focus on model development.

Key takeaways
  • Hugging Face Jobs integrates with GitHub CI.
  • Migration enables scalable compute resources.
  • GitHub repositories can be easily integrated.
HHugging Face Blog#hugging-face#github#ci-cd
otherApr 29

DeepInfra on Hugging Face Inference Providers 🔥

DeepInfra has joined Hugging Face as an inference provider, expanding access to optimized model serving. This partnership allows builders to deploy models with DeepInfra's performance-optimized infrastructure. You can now use DeepInfra's GPU-accelerated serving for Hugging Face-hosted models. The addition of DeepInfra brings more choices for scalable and cost-effective model deployment.

Key takeaways
  • DeepInfra joins Hugging Face as an inference provider.
  • Offers GPU-accelerated model serving for Hugging Face models.
  • Expands deployment options for builders.
HHugging Face Blog#hugging-face#inference#model-serving
modelsApr 24

DeepSeek-V4: a million-token context that agents can actually use

DeepSeek-V4 offers a 1M token context window, making it suitable for long-range tasks. The model is available on Hugging Face for download and integration into applications. A 1M token context enables more comprehensive text analysis and generation. This capability is particularly useful for builders working on tasks that require processing large volumes of text.

Key takeaways
  • 1M token context window for comprehensive text analysis.
  • Available on Hugging Face for download and integration.
  • Enables long-range tasks with large text volumes.
HHugging Face Blog#long-context#open-source#hugging-face
otherApr 15

Meet HoloTab by HCompany. Your AI browser companion.

HCompany released HoloTab, an AI browser companion available on Hugging Face. The tool aims to assist users in their browsing experience with AI-driven features. You can explore HoloTab's capabilities on the Hugging Face platform. Builders may find HoloTab useful for integrating AI into their browser-based applications.

Key takeaways
  • HoloTab is an AI browser companion.
  • Available on Hugging Face.
  • Assists users with AI-driven features.
HHugging Face Blog#ai-tools#browser-extension#hugging-face
otherMar 10

Introducing Storage Buckets on the Hugging Face Hub

The Hugging Face Hub now offers Storage Buckets, a feature allowing users to organize and share datasets, models, and other files in a more structured way. This update aims to improve collaboration and data management for AI projects. You can create and manage buckets through the Hub's interface or API. Storage Buckets supports flexible access controls.

Key takeaways
  • Storage Buckets organize datasets, models, and files on the Hugging Face Hub.
  • Buckets support flexible access controls.
  • Management is available through both interface and API.
HHugging Face Blog#hugging-face#data-management#collaboration
otherFeb 20

Train AI models with Unsloth and Hugging Face Jobs for FREE

Unsloth and Hugging Face Jobs offer free training for AI models. The program targets builders and researchers looking to fine-tune models without incurring high costs. This initiative aims to make AI model training more accessible. You can take advantage of this opportunity to train models at no cost.

Key takeaways
  • Free training for AI models is available through Unsloth and Hugging Face Jobs.
  • The program is aimed at builders and researchers.
  • No costs are associated with training models through this initiative.
HHugging Face Blog#free-training#ai-models#hugging-face
toolsFeb 13

Custom Kernels for All from Codex and Claude

Hugging Face now supports custom CUDA kernels for all users, enabling developers to optimize performance-critical code. This feature allows for fine-grained control over GPU acceleration, targeting applications like computer vision and natural language processing. Builders can now deploy custom kernels to improve model performance and reduce latency. This update is available through Hugging Face's API and SDK.

Key takeaways
  • Custom CUDA kernels now available for all Hugging Face users.
  • Enables fine-grained control over GPU acceleration.
  • Targets performance-critical applications like computer vision and NLP.
HHugging Face Blog#custom-kernels#gpu-acceleration#hugging-face
otherFeb 3

The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+

The open-source AI ecosystem has grown significantly since the release of DeepSeek, with Hugging Face playing a key role in fostering collaboration and innovation. The ecosystem has expanded to include new models, tools, and communities, driving progress in AI development. Builders can now access a wide range of open-source AI resources, enabling them to create and deploy AI solutions more efficiently. This growth has positioned the open-source AI ecosystem for continued success.

Key takeaways
  • Hugging Face has played a key role in fostering collaboration and innovation in the open-source AI ecosystem.
  • The ecosystem has expanded to include new models, tools, and communities.
  • Builders can access a wide range of open-source AI resources.
HHugging Face Blog#open-source#ai-ecosystem#hugging-face
modelsDec 15

CUGA on Hugging Face: Democratizing Configurable AI Agents

IBM Research has released CUGA, a configurable AI agent framework, on Hugging Face. CUGA allows developers to create customized AI agents for various applications. The framework is designed to be flexible and adaptable, enabling builders to deploy AI agents in different environments. You can access CUGA on Hugging Face and explore its capabilities.

Key takeaways
  • CUGA is now available on Hugging Face.
  • The framework enables creation of customized AI agents.
  • CUGA is designed for flexibility and adaptability.
HHugging Face Blog#configurable-ai-agents#hugging-face#open-source
modelsDec 11

Codex is Open Sourcing AI models

Codex is open-sourcing AI models through the Hugging Face platform. This move allows developers to access and build upon Codex's models, promoting collaboration and innovation in the AI community. By making its models open-source, Codex aims to accelerate AI development and adoption. Developers can now explore and integrate Codex's models into their projects.

Key takeaways
  • Codex models are now open-source on Hugging Face.
  • Developers can access and build upon these models.
  • Open-sourcing aims to accelerate AI development.
HHugging Face Blog#open-source#hugging-face#ai-models
toolsDec 5

Introducing swift-huggingface: The Complete Swift Client for Hugging Face

The Hugging Face team has released a new Swift client, swift-huggingface, providing a native integration for Apple ecosystem developers. This client enables direct access to Hugging Face models and services from Swift applications. Builders can now easily integrate Hugging Face capabilities into their iOS, macOS, watchOS, and tvOS projects. The client supports core features like model downloads, inference, and API access.

Key takeaways
  • Native Swift client for Hugging Face models and services.
  • Enables integration with iOS, macOS, watchOS, and tvOS apps.
  • Supports model downloads, inference, and API access.
HHugging Face Blog#hugging-face#swift#apple-ecosystem
toolsNov 17

Easily Build and Share ROCm Kernels with Hugging Face

Hugging Face now supports building and sharing ROCm kernels, enabling developers to optimize and deploy AI models on AMD hardware. This integration allows for more flexible model deployment across different hardware platforms. You can now easily build, test, and share ROCm kernels using Hugging Face's tools. This development is particularly relevant for builders working with AI models on AMD-based systems.

Key takeaways
  • Hugging Face supports building and sharing ROCm kernels.
  • Enables optimization and deployment of AI models on AMD hardware.
  • Facilitates flexible model deployment across hardware platforms.
HHugging Face Blog#rocm#hugging-face#amd
otherOct 27

huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning

The Hugging Face Hub has reached v1.0 after five years of development, providing a platform for open machine learning with over 100,000 models and datasets. It supports a wide range of tasks and has become a central hub for the open ML community. You can access and contribute to the hub's resources.

Key takeaways
  • 100,000+ models and datasets available
  • Five years of development leading to v1.0 release
  • Central platform for open machine learning community
HHugging Face Blog#open-source#machine-learning#hugging-face
toolsOct 21

Unlock the power of images with AI Sheets

Hugging Face released AI Sheets, a tool for building image-based applications with AI. AI Sheets allows users to create custom image processing workflows. The tool is designed to make it easier for developers to integrate image-based AI into their applications. Builders can use AI Sheets to create custom image processing workflows.

Key takeaways
  • Hugging Face releases AI Sheets for image-based applications.
  • AI Sheets enables custom image processing workflows.
  • Developers can integrate AI Sheets into their applications.
HHugging Face Blog#hugging-face#image-processing#ai-tools
otherSep 17

Public AI on Hugging Face Inference Providers 🔥

Hugging Face has launched Public AI, a new service offering access to a range of open and closed AI models via API. The service aims to provide a unified interface for developers to deploy and manage AI models. Public AI supports multiple models from various providers. You can use it to simplify AI model deployment and management.

Key takeaways
  • Hugging Face launches Public AI for unified model access.
  • Supports open and closed models from multiple providers.
  • Simplifies deployment and management for developers.
HHugging Face Blog#hugging-face#inference#api
modelsSep 10

Fine-tune Any LLM from the Hugging Face Hub with Together AI

Together AI now offers fine-tuning for any LLM on the Hugging Face Hub, allowing builders to adapt models to specific tasks. This service supports a wide range of open-weights models, enabling customization without requiring significant computational resources. You can fine-tune models for tasks like text classification, sentiment analysis, and more. The integration aims to make model customization more accessible.

Key takeaways
  • Fine-tune any Hugging Face Hub LLM with Together AI.
  • Supports a wide range of open-weights models.
  • Customization for tasks like text classification and sentiment analysis.
HHugging Face Blog#fine-tuning#hugging-face#open-source
modelsSep 2

Make your ZeroGPU Spaces go brrr with ahead-of-time compilation

Hugging Face introduces ahead-of-time compilation for ZeroGPU Spaces, enabling faster inference and lower latency. This feature allows for optimized performance without requiring specialized hardware. You can now deploy high-performance GPU-accelerated models in your Spaces with improved efficiency.

Key takeaways
  • Ahead-of-time compilation enabled for ZeroGPU Spaces.
  • Faster inference and lower latency without specialized hardware.
  • Optimized performance for GPU-accelerated models.
HHugging Face Blog#hugging-face#zerogpu#aot-compilation
toolsAug 8

Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training

The Hugging Face Accelerate library now supports ND-Parallel for efficient multi-GPU training. This feature allows for faster training times and better scalability. You can use it to train large models across multiple GPUs. The guide provides step-by-step instructions for implementation.

Key takeaways
  • Hugging Face Accelerate supports ND-Parallel for multi-GPU training.
  • ND-Parallel enables faster training and better scalability.
  • The feature is useful for training large models across multiple GPUs.
HHugging Face Blog#multi-gpu-training#hugging-face#scalability
modelsAug 5

Welcome GPT OSS, the new open-source model family from OpenAI!

OpenAI announced GPT OSS, a new open-source model family, on the Hugging Face blog. The move marks a significant shift towards openness in AI development. You can now access and build on GPT OSS models. This development may change how you approach AI model selection.

Key takeaways
  • OpenAI released an open-source model family called GPT OSS.
  • GPT OSS models are available on the Hugging Face platform.
  • This move may impact your AI model selection process.
HHugging Face Blog#open-source#openai#hugging-face
toolsJul 25

Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨

The Hugging Face team released a new CLI tool called `hf`, offering a faster and more user-friendly interface for interacting with Hugging Face models and repositories. This new tool aims to improve the overall experience for developers and researchers working with Hugging Face's offerings. The `hf` CLI is designed to be more efficient and easier to use than the previous interface.

Key takeaways
  • Faster and friendlier interface for Hugging Face models.
  • Improves experience for developers and researchers.
  • Designed to be more efficient and easier to use.
HHugging Face Blog#hugging-face#cli-tools#developer-tools
researchJul 10

Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models

Researchers applied test-time reinforcement learning search to large formal reasoning models, improving performance on mathematical proof generation. The Kimina-Prover system was released on the Hugging Face platform. This development may interest builders working on AI-assisted formal verification and proof generation. The approach could enhance the efficiency of formal reasoning tasks.

Key takeaways
  • Test-time RL search improves performance on mathematical proof generation.
  • Kimina-Prover system released on Hugging Face platform.
  • Potential applications in AI-assisted formal verification.
HHugging Face Blog#formal-reasoning#reinforcement-learning#hugging-face
researchJul 10

Asynchronous Robot Inference: Decoupling Action Prediction and Execution

Researchers propose asynchronous robot inference, decoupling action prediction and execution to improve real-time performance. This approach enables robots to act on predicted actions while continuing to predict future actions, reducing latency. You can explore the code on Hugging Face. The method is particularly useful for applications requiring fast and efficient decision-making.

Key takeaways
  • Decouples action prediction and execution for better real-time performance.
  • Reduces latency in robot decision-making.
  • Code available on Hugging Face.
HHugging Face Blog#robotics#async-inference#hugging-face
toolsJul 8

Efficient MultiModal Data Pipeline

Hugging Face released Efficient MultiModal Data Pipeline (MMDP), a library for efficient multimodal data processing. MMDP allows you to preprocess and transform multimodal data in a scalable and efficient manner. This library is particularly useful for builders working with large-scale multimodal datasets. MMDP supports various data types and formats.

Key takeaways
  • MMDP supports various data types and formats.
  • Scalable and efficient multimodal data processing.
  • Useful for large-scale multimodal datasets.
HHugging Face Blog#multimodal#data-pipeline#hugging-face
modelsJul 8

SmolLM3: smol, multilingual, long-context reasoner

SmolLM3 is a new multilingual, long-context LLM released on the Hugging Face platform. It is designed for reasoning tasks and offers a unique combination of capabilities. The model is available for download and use. You can explore its features and performance on the Hugging Face blog.

Key takeaways
  • SmolLM3 is multilingual and supports long-context reasoning.
  • The model is available on the Hugging Face platform.
  • It is designed for tasks that require reasoning capabilities.
HHugging Face Blog#multilingual-llm#long-context#hugging-face
modelsJul 1

Training and Finetuning Sparse Embedding Models with Sentence Transformers

The Hugging Face Transformers library now supports sparse embedding models through Sentence Transformers. You can train and fine-tune sparse models using the library's API. Sparse embedding models are useful for applications where memory and compute efficiency are critical. This update enables builders to deploy more efficient models in production.

Key takeaways
  • Hugging Face Transformers supports sparse embedding models via Sentence Transformers.
  • Sparse models are useful for memory and compute efficiency.
  • Enables deployment of efficient models in production.
HHugging Face Blog#sparse-embeddings#sentence-transformers#hugging-face
modelsJun 27

Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub

NVIDIA has released the Llama Nemotron Nano VLM on the Hugging Face Hub. The model is a vision-language model available for download and local deployment. Builders can use it for applications requiring visual understanding. The release expands the open-weights ecosystem.

Key takeaways
  • Available on Hugging Face Hub for download.
  • A vision-language model for visual understanding applications.
  • Released by NVIDIA as an open-weights model.
HHugging Face Blog#open-source#vision-llm#hugging-face
otherJun 16

Groq on Hugging Face Inference Providers 🔥

Groq has joined Hugging Face as an inference provider, offering optimized performance for large language models. This partnership enables seamless deployment of AI models on Groq's hardware. You can now deploy models on Groq's infrastructure through the Hugging Face platform. Builders can leverage Groq's performance for their AI applications.

Key takeaways
  • Groq joins Hugging Face as an inference provider.
  • Enables deployment of AI models on Groq's hardware via Hugging Face.
  • Partnership offers optimized performance for large language models.
HHugging Face Blog#inference#hugging-face#hardware
otherJun 12

Featherless AI on Hugging Face Inference Providers 🔥

Featherless AI has joined Hugging Face as an inference provider, expanding access to its optimized models via Hugging Face's API. This integration allows developers to deploy Featherless models directly through Hugging Face's platform. Builders can now access Featherless' optimized models without leaving the Hugging Face ecosystem. The partnership aims to streamline model deployment and enhance developer experience.

Key takeaways
  • Featherless AI is now an inference provider on Hugging Face.
  • Developers can deploy Featherless models via Hugging Face's API.
  • Partnership aims to simplify model deployment for developers.
HHugging Face Blog#inference#hugging-face#model-deployment
toolsJun 12

Learn the Hugging Face Kernel Hub in 5 Minutes

The Hugging Face Kernel Hub is a new platform for sharing and deploying optimized ML kernels. It allows users to discover, download, and deploy high-performance kernels for various ML frameworks. Builders can leverage optimized kernels to accelerate their ML workflows. The hub supports multiple frameworks and hardware platforms.

Key takeaways
  • Hugging Face launches Kernel Hub for optimized ML kernels.
  • Accelerates ML workflows with high-performance kernels.
  • Supports multiple frameworks and hardware.
HHugging Face Blog#hugging-face#ml-frameworks#optimized-kernels
modelsMay 21

Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance

The TII UAE team released Falcon-H1, a new family of hybrid-head language models that aim to improve efficiency and performance. These models are designed to provide a better trade-off between accuracy and computational resources. You can explore the Falcon-H1 models on the Hugging Face platform. The release includes several pre-trained models and code to get started.

Key takeaways
  • Falcon-H1 models offer improved efficiency and performance.
  • Available on Hugging Face with pre-trained models and code.
  • Designed for a better trade-off between accuracy and computational resources.
HHugging Face Blog#hybrid-head#language-models#hugging-face
otherMay 14

Improving Hugging Face Model Access for Kaggle Users

Hugging Face has integrated with Kaggle to improve model access for data science and machine learning practitioners. The integration allows users to seamlessly browse, use, and train models directly within Kaggle Notebooks. This development streamlines workflows and enhances collaboration between data scientists and machine learning engineers.

Key takeaways
  • Hugging Face models now accessible directly within Kaggle Notebooks.
  • Integration aims to streamline workflows for data science and ML practitioners.
  • Enhances collaboration between data scientists and ML engineers.
HHugging Face Blog#hugging-face#kaggle#model-integration
otherApr 16

Cohere on Hugging Face Inference Providers 🔥

Cohere has joined Hugging Face as an inference provider, expanding access to its models through the Hugging Face ecosystem. This partnership allows developers to deploy Cohere models directly within Hugging Face's inference platform. You can now use Cohere's models with Hugging Face's tools and services. The integration aims to provide a seamless experience for deploying and managing AI models.

Key takeaways
  • Cohere models available on Hugging Face inference platform.
  • Developers can deploy Cohere models directly within Hugging Face.
  • Partnership aims to simplify AI model deployment and management.
HHugging Face Blog#inference#hugging-face#model-deployment
modelsApr 11

Visual Salamandra: Pushing the Boundaries of Multimodal Understanding

The Visual Salamandra 7B model is a new multimodal model that integrates text and image understanding. It is based on the LLaMA-2 architecture and has achieved state-of-the-art results on several benchmarks. The model is available on the Hugging Face platform for developers to use and build applications. You can leverage this model for tasks that require both text and image processing.

Key takeaways
  • Integrates text and image understanding
  • Based on LLaMA-2 architecture
  • Achieved state-of-the-art results on several benchmarks
HHugging Face Blog#multimodal#llms#hugging-face
modelsApr 5

Welcome Llama 4 Maverick & Scout on Hugging Face

Meta has released Llama 4 models Maverick and Scout on Hugging Face. The models are open-weights and available for download. You can deploy them locally or use them as a base for further fine-tuning. This release expands the Llama family of models.

Key takeaways
  • Llama 4 models are open-weights and downloadable.
  • Maverick and Scout are the latest additions to the Llama family.
  • Models are available on Hugging Face for local deployment or fine-tuning.
HHugging Face Blog#open-source#hugging-face#local-llm
modelsMar 18

NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets

NVIDIA announced new open models and datasets for physical AI developers at GTC 2025. The release includes simulation tools and pre-trained models for robotics and autonomous systems. You can access these resources through the Hugging Face platform. This move aims to accelerate development in physical AI.

Key takeaways
  • NVIDIA releases new open models and datasets for physical AI.
  • Resources available on Hugging Face platform.
  • Targets robotics and autonomous systems development.
HHugging Face Blog#physical-ai#open-models#hugging-face
otherFeb 18

Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥

Hugging Face has added three new serverless inference providers: Hyperbolic, Nebius AI Studio, and Novita. This expansion offers builders more choices for deploying and serving AI models. The addition of these providers increases competition in the serverless inference market. You can now explore these new options for your AI model deployment needs.

Key takeaways
  • Three new serverless inference providers added.
  • Increased competition in serverless inference market.
  • More deployment choices for AI models.
HHugging Face Blog#serverless-inference#model-deployment#hugging-face
otherFeb 14

Welcome Fireworks.ai on the Hub 🎆

Fireworks.ai has joined Hugging Face Hub, bringing their models and expertise to the platform. This partnership enables developers to access Fireworks.ai's models and integrate them into their applications. Builders can now explore new models and capabilities on the Hub. The addition expands the range of available models for various use cases.

Key takeaways
  • Fireworks.ai models are now available on Hugging Face Hub.
  • Developers can integrate Fireworks.ai models into their applications.
  • Expanded model offerings on the Hub for various use cases.
HHugging Face Blog#hugging-face#open-source#model-hub
modelsFeb 10

The Open Arabic LLM Leaderboard 2

The Open Arabic LLM Leaderboard 2 has been released on Hugging Face, providing updated rankings of Arabic-language models. The leaderboard evaluates models on tasks like sentiment analysis and question-answering. You can use this leaderboard to compare and select suitable models for your Arabic-language NLP projects. The leaderboard aims to support the development of more capable Arabic-language models.

Key takeaways
  • Leaderboard evaluates models on Arabic-language tasks.
  • Supports development of more capable Arabic-language models.
  • Available on Hugging Face platform.
HHugging Face Blog#arabic-llm#leaderboard#hugging-face
otherJan 28

Welcome to Inference Providers on the Hub 🔥

Hugging Face has launched Inference Providers on the Hub, a new feature that allows users to deploy and manage models from multiple providers in one place. This centralized hub enables builders to easily discover, deploy, and manage inference endpoints for various AI models. By supporting multiple providers, Hugging Face aims to simplify the deployment process and increase model accessibility. You can now explore and deploy models from different providers using the Hub.

Key takeaways
  • Centralized deployment and management of models from multiple providers.
  • Simplified deployment process for AI models.
  • Increased model accessibility through a single hub.
HHugging Face Blog#inference#model-deployment#hugging-face
otherJan 22

Hugging Face and FriendliAI partner to supercharge model deployment on the Hub

Hugging Face and FriendliAI have partnered to improve model deployment on the Hugging Face Hub. The partnership aims to provide users with more efficient and scalable model deployment options. This collaboration is expected to benefit builders who use the Hub for model hosting and deployment. The integration will enable faster and more reliable model serving.

Key takeaways
  • Hugging Face partners with FriendliAI for model deployment.
  • Partnership targets improved efficiency and scalability on the Hub.
  • Integration enables faster model serving.
HHugging Face Blog#model-deployment#hugging-face#partnerships
otherNov 26

Rearchitecting Hugging Face Uploads and Downloads

Hugging Face has rearchitected its upload and download infrastructure to improve performance and reliability. The changes enable faster and more efficient model sharing and access. This update impacts how users interact with models and datasets on the platform. You can expect better performance when uploading and downloading models.

Key takeaways
  • Faster upload and download speeds.
  • Improved reliability for model sharing.
  • Enhanced user experience on Hugging Face platform.
HHugging Face Blog#hugging-face#infrastructure#performance
modelsNov 26

SmolVLM - small yet mighty Vision Language Model

The SmolVLM model is a new vision language model that is small yet efficient. It is designed to be a compact and capable model for visual tasks. The model is available on the Hugging Face platform. You can use it for various applications that require vision and language understanding.

Key takeaways
  • SmolVLM is a small yet efficient vision language model.
  • Available on Hugging Face platform.
  • Designed for compact and capable visual tasks.
HHugging Face Blog#vision-language-model#small-models#hugging-face
otherNov 12

Share your open ML datasets on Hugging Face Hub!

The Hugging Face Hub now allows researchers to share their open ML datasets directly on the platform. This enables easier discovery and access to datasets for builders and researchers. By centralizing dataset sharing, the Hub aims to accelerate ML research and development. You can now upload and share your datasets with the community.

Key takeaways
  • Hugging Face Hub supports direct dataset sharing.
  • Easier discovery and access to open ML datasets.
  • Centralized platform for ML research and development.
HHugging Face Blog#open-source#dataset-sharing#hugging-face