Items tagged with “Hugging Face”.
Scaleway is now a supported Inference Provider on the Hugging Face Hub, enabling serverless inference directly on model pages with JS and Python SDKs. Access popular open-weight models and enjoy scalable, low-latency AI workflows.
A report on using PyTorch Ahead-of-Time (AoT) compilation to accelerate ZeroGPU Spaces on Nvidia H200 hardware, including setup, quantization options, dynamic shapes, and practical speedups.
Learn how PyTorch AoT compilation speeds up ZeroGPU Spaces on Nvidia H200 GPUs, enabling instant reloads, FP8 quantization, dynamic shapes, and practical speedups (1.3x–1.8x) for Flux, Wan, and LTX models.
Learn how PyTorch AoT compilation speeds up ZeroGPU Spaces by exporting a compiled model once and reloading instantly, with FP8 quantization, dynamic shapes, and careful integration with the Spaces GPU workflow.
A comprehensive look at connecting Claude to Hugging Face Spaces and MCP Server to generate high-quality images, including realistic textures and accurate text rendering with FLUX.1-Krea-dev and Qwen-Image.
The Nemotron Nano 2 9B is an open enterprise‑grade reasoning model with a Hybrid Transformer–Mamba backbone and a configurable thinking budget, delivering leading accuracy and 6x throughput for edge and hybrid deployments.
Learn how to connect Claude to Hugging Face Spaces via the MCP Server to generate images with Krea and Qwen-Image, leverage free credits, and explore the Hugging Face AI App Directory.
Open Nemotron Nano 2 9B delivers leading accuracy and up to 6x throughput with a Hybrid Transformer–Mamba backbone and a configurable thinking budget, aimed at edge, PC and enterprise AI agents.
A step-by-step guide to authoring, building, versioning, and publishing production-ready CUDA kernels using the Hugging Face kernel-builder and reproducible Nix builds.
The Model Context Protocol (MCP) enables agentic models to access research tools via natural language. Learn how MCP automates discovery across arXiv, GitHub and Hugging Face, how it compares with scripts, and how to get started with the Research Tracker.
A practical guide to developing, building for multiple architectures, and deploying CUDA kernels with Hugging Face Kernel Builder. Learn how to create a robust workflow from local development to Hub-based distribution.
A practical walkthrough of Hugging Face's kernel-builder for developing, compiling, and deploying production-ready CUDA kernels across PyTorch, with reproducible builds, multi-arch support, and hub-based distribution.
Explains the Model Context Protocol (MCP) for research discovery and how AI can orchestrate research tools across arXiv, GitHub, and Hugging Face via natural language.
FilBench evaluates LLM performance for Tagalog, Filipino, and Cebuano across cultural knowledge, NLP, reading comprehension, and generation, revealing efficiency and translation insights for SEA-focused models and GPT-4o.
TextQuests is a benchmark testing LLM agents in 25 classic text-based Infocom games, emphasizing long-context reasoning and autonomous exploration.
FilBench is a comprehensive evaluation suite to assess LLM capabilities for Tagalog, Filipino, and Cebuano across cultural knowledge, NLP, reading comprehension, and generation, using a rigorous, historically informed methodology.
AI Sheets is an open-source, no-code tool from Hugging Face for building, transforming and enriching datasets using thousands of open models or local models. Try it in Spaces or deploy locally.
Overview of Accelerate's ND‑Parallel capabilities: combining data, tensor, sharded and context parallelism with Axolotl to scale large-model training across multi‑GPU and multi‑node environments.
A concise resource on composing multiple parallelism strategies (DP, FSDP, TP, CP) with Accelerate and Axolotl to train large models across many GPUs, with guidance on configuration, use cases, and trade‑offs.
AI Sheets is an open-source, no-code tool for building, enriching, and transforming datasets with AI models. Deployable locally or on the Hub, it supports thousands of open models and lets you iterate with prompts, few-shot feedback, and model comparisons.
TRL expands multimodal alignment for Vision-Language Models with GRPO, GSPO, MPO, and native SFT support, plus ready-to-run scripts and notebooks to streamline post-training alignment.
Overview of TRL's multimodal alignment methods for vision-language models: GRPO, GSPO, MPO, plus native SFT support and DPO-based baselines.
OpenAI releases two open-weight, mixture-of-experts models—GPT OSS 120B and GPT OSS 20B—utilizing MXFP4 4-bit quantization. They’re licensed Apache 2.0 with a minimal usage policy and are accessible via Hugging Face Inference Providers for on-device, on-prem, and cloud deployments.
OpenAI releases GPT OSS, a pair of 120B and 20B mixture-of-experts models with MXFP4 4-bit quantization, licensed Apache 2.0, and delivered via Hugging Face Inference Providers for on-device and server deployments.
Two open-weight OpenAI models (gpt-oss-120b and gpt-oss-20b) using mixture-of-experts and MXFP4 quantization for fast, memory-efficient reasoning. Licensed Apache 2.0; designed for private/local deployments and on-device use, with Hugging Face Inference Providers integration.
Explore how Gradio MCP servers enable an LLM-powered shopping assistant that browses stores, selects garments, and shows virtual try-ons with IDM-VTON, all integrated via VS Code AI Chat.
Explore how Gradio MCP servers connect LLMs to Hugging Face models, enabling an AI shopping assistant that browses stores and performs virtual try-ons using IDM-VTON.
Trackio is an open-source, free Python library for experiment tracking with a local Gradio dashboard and optional syncing to Hugging Face Spaces for simple sharing and collaboration.
Open-source, free Python library for experiment tracking with a local Gradio dashboard that can sync to Hugging Face Spaces for easy sharing and collaboration. Drop-in replacement for wandb with a lightweight beta design.
Hugging Face expands data efficiency with Parquet CDC, enabling content-defined chunking in PyArrow and Pandas and leveraging the Xet storage layer to dramatically reduce data transfer and storage costs.
Parquet Content-Defined Chunking (CDC) extends PyArrow and Pandas, enabling efficient, cross-repository deduplication on Hugging Face’s Xet storage layer to cut Parquet transfer and storage costs.
Hugging Face renames its CLI to hf, reorganizes commands under a resource-action pattern, and introduces Hugging Face Jobs, while preserving the legacy huggingface-cli for migration.
Overview of the renamed Hugging Face CLI, its reorganized resource-based commands, and the new Jobs service, plus setup, usage, and migration notes.
Enable Parquet CDC with Hugging Face's Xet storage to deduplicate data chunks across files and repositories, reducing upload/download size and storage costs.
This article explains how a Hugging Face optimization recipe speeds up LoRA inference on Flux using Diffusers and PEFT, delivering up to ~2.3x speedups and detailing hotswapping, FP8 quantization, and memory-management techniques.
Open-source TimeScope tests long-video understanding by inserting short needle clips into base videos (1 minute to 8 hours), evaluating retrieval, synthesis, localization, and motion analysis.
TimeScope introduces a new open-source benchmark to measure how vision-language models process long videos by inserting short needles and evaluating retrieval, synthesis, localization, and motion analysis.
Overview of Arc Institute's Virtual Cell Challenge, its STATE baseline, and the implications for in silico cell perturbation modeling and context generalization in transcriptomics.
A deep dive into FutureBench, a benchmark that tests AI agents on forecasting future events using real-world data sources, with a focus on reasoning under uncertainty and verifiable outcomes.
A deep dive into Consilium, the multi-LLM platform that enables models to discuss, debate, and reach consensus via MCP servers and a visual Gradio roundtable.
Overview of Gradio MCP server improvements in version 5.38.0, including File Upload support, real-time progress streaming, OpenAPI integration, header handling, and improved tool descriptions.
Ettin introduces the first state-of-the-art paired encoder-only and decoder-only models trained with identical data and recipes, measuring apples-to-apples performance across tasks and scales.