---
title: "Hugging Face"
description: "AI platform and community providing machine learning models, datasets, libraries, and tools for building AI applications."
---

# Hugging Face
> AI platform and community providing machine learning models, datasets, libraries, and tools for building AI applications.

## Articles

### [Agentic Resource Discovery: Let agents search](https://yomu.fyi/post/agentic-resource-discovery-let-agents-search.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: ben burtenshaw, shaun smith
- Published: Jun 17, 2026
- Type: Explainer

Agentic Resource Discovery (ARD) is a draft, open specification for discovering agent capabilities at runtime, addressing a model in which users and developers must pre-install, integrate, and maintain each MCP tool, skill, or A2A agent. It defines a static ai-catalog.json manifest and a dynamic POST /search registry API, using indexed signals such as publisher identity, representative queries, compliance attestations, and tags to move capability selection outside the LLM. Hugging Face's Discover Tool adapts Hub semantic search into ARD catalog entries for running Spaces, exposing skills, MCP servers, or raw Space metadata according to the requested media type and wrapping agents.md files into installable SKILL.md artifacts. The tool is available through the hf CLI, REST, and MCP, while planned work includes federation modes and Hub support for profile-level manifests.


### [Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP](https://yomu.fyi/post/profiling-in-pytorch-part-2-from-nn-linear-to-a-fused-mlp.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Aritra Roy Gosthipaty, Rémi Ouazan Reboul, Sergio Paniego, Pedro Cuenca, Sayak Paul
- Published: Jun 11, 2026
- Type: Tutorial

Part 2 of the series examines how PyTorch profiler traces change from a single bias-enabled nn.Linear to a three-layer MLP with an intervening activation, using scripts run on an NVIDIA A100-SXM4-80GB GPU. It explains that nn.Linear represents y = x @ w.T + b, dispatches aten::addmm, and folds bias addition into the cuBLAS GEMM epilogue, while aten::t only rewrites weight strides and launches no GPU kernel. For the MLP, eager execution uses three GEMMs plus separate activation and multiplication kernels, whereas torch.compile fuses the latter operations and keeps the intermediate out of HBM, while leaving the GEMMs unchanged. A hand-written Liger Triton kernel provides the same fusion without Dynamo guards or compile latency, trading Inductor’s shape-specialized speed for generic execution across changing shapes.


### [How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces](https://yomu.fyi/post/how-an-agent-built-a-3d-paris-gallery-by-chaining-two-hugging-face-spa.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Mishig Davaadorj
- Published: Jun 9, 2026
- Type: Explainer

A coding agent built a 3D Paris gallery by chaining two Hugging Face Spaces: an image-generation Space produced dark-background monument images, and VAST-AI/TripoSplat reconstructed each single image as a 3D Gaussian splat. It then handled integration work by correcting the splats’ Y-down orientation, auto-framing monuments, compressing .ply files to .ksplat at about one-third the size, and building and deploying a static Three.js viewer. The Spaces’ agents.md files provided schemas, call and polling templates, file-upload instructions, and authentication guidance, allowing the agent to call them without a client library. The same pipeline produced six-monument galleries for Egypt and Japan after the prompts changed. The account presents callable, documented multimedia components as a way to reduce integration work and make new multimedia applications cheaper to create.


### [Migrating Your GitHub CI to Hugging Face Jobs](https://yomu.fyi/post/migrating-your-github-ci-to-hugging-face-jobs.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Abubakar Abid
- Published: Jun 9, 2026
- Type: Tutorial

Trackio's GitHub Actions CI was limited by generic hosted machines, maintenance-related delays, and lack of readily available GPU runners, while the project needed CPU checks and CUDA-based tests. The setup keeps GitHub Actions as the CI coordinator and uses a dispatcher Space plus the huggingface/jobs-actions bridge to launch ephemeral GitHub runners inside Hugging Face Jobs, selected through labels such as hf-jobs-cpu-upgrade and hf-jobs-t4-small. The guide covers duplicating and configuring the dispatcher, creating a GitHub App, supplying runner credentials and an HF token, changing runs-on, choosing Docker images, and validating runs and logs; Playwright and NVIDIA CUDA images are used for CPU and GPU examples. In Trackio, the CPU job took 1m10s versus a 1m40s GitHub ubuntu-latest baseline, while the GPU check passed in 45s and cost less than a cent at the t4-small rate; logs were available through both systems.


### [The Open Source Community is backing OpenEnv for Agentic RL](https://yomu.fyi/post/the-open-source-community-is-backing-openenv-for-agentic-rl.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: ben burtenshaw, Joseph Spisak, Lysandre, Davide Testuggine, will brown, Joy Liu, Peyton Walters, Chris Wing, Daniel (Unsloth), Andrew Zhou, Govind Kamtamneni, Michael Han, Hamid Shojanazeri, Sanyam Bhutani, Zach Wentz, Emre Guven, Lewis Tunstall, Sergio Paniego, Banghua Zhu, Haoguang Cai
- Published: Jun 8, 2026
- Type: Announcement

OpenEnv is becoming a community-coordinated, open-source tool for building agentic execution environments such as terminals and browsers, with the stated goal of helping train open-source agents. Starting now, a committee including Meta-PyTorch, Reflection, Unsloth, Modal, Prime Intellect, Nvidia, Mercor, Fleet AI, Microsoft, Hugging Face, and RadixArk will coordinate the project, which now lives at huggingface/OpenEnv and is supported or adopted by numerous AI organizations. Technically, OpenEnv is being narrowed to an interoperability and protocol layer: environments expose a Gymnasium-style reset(), step(), and state() API through client/server deployments, standard HTTP or WebSocket protocols, Docker packaging, and MCP compatibility. It does not define rewards or training loops; those remain in specialized libraries, while OpenEnv connects harnesses, environments, and trainers across ecosystems. Planned work includes external rewards, dataset-backed tasksets, harness integrations, end-to-end examples, and automatic environment validation.


### [Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI](https://yomu.fyi/post/nemotron-3-5-content-safety-customizable-multimodal-safety-for-global.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Varun Singh, Isabel Hulseman, Anuj Doshi, Shyamala Prayaga
- Published: Jun 4, 2026
- Type: Announcement

Nemotron 3.5 Content Safety is NVIDIA’s 4B-parameter model for evaluating user prompts, optional images, and optional assistant responses together, with multilingual coverage and enterprise-specific policy enforcement. It extends Nemotron 3 by accepting natural-language custom policies, producing optional auditable reasoning traces, and supporting binary verdicts, category-labelled verdicts, or THINK mode; disabling THINK preserves the default low-latency path. Built on Google Gemma 3 4B IT with a LoRA adapter and a 128K context window, it uses the Aegis 2.0 taxonomy of 13 core categories and 10 subcategories, and targets deployment on GPUs with 8GB or more of VRAM. The accompanying multimodal, multilingual dataset includes concise reasoning traces, while reported results average 96.5% on Multilingual Aegis, 88.8% on RTP-LX, and about 85% across the evaluated benchmark set.


### [Designing the hf CLI as an agent-optimized way to work with the Hub](https://yomu.fyi/post/designing-the-hf-cli-as-an-agent-optimized-way-to-work-with-the-hub.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Célina Hanouti, Lucain Pouget
- Published: Jun 4, 2026
- Type: Benchmark

The post presents a redesign of hf, the Hugging Face Hub’s official CLI, for both human users and coding agents that download, upload, manage repositories, run Jobs, and administer other Hub resources. The CLI detects agents through environment variables, switches to compact, complete TSV output, and supports explicit human, agent, JSON, and quiet formats; agent mode was introduced in hf v1.9.0. Next-command hints, stderr separation, non-interactive failure messages, retry-safe operations, confirmations, and dry-run previews support multi-step automation without removing human-friendly terminal behavior. Benchmarks report equal-or-better success with roughly 1.3× to 1.8× fewer tokens than curl or the SDK on comparable tasks, and up to 6× fewer on complex workflows; the generated hf-cli skill reduced tool calls by about 30% without reducing token use or improving reliability.


### [Direct Preference Optimization Beyond Chatbots](https://yomu.fyi/post/direct-preference-optimization-beyond-chatbots.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Erick Lachmann, Gabriel Pimenta de Freitas Cardoso, Francisco de Almeida Rocha Alves
- Published: Jun 3, 2026
- Type: Explainer

DharmaOCR applies Direct Preference Optimization (DPO) beyond chat alignment to reduce text degeneration in structured OCR, where outputs are either acceptable transcriptions or failure loops. In a benchmark of Brazilian Portuguese structured-document OCR, vanilla degeneration rates among open-source model families ranged from below 1% to above 33%, while supervised fine-tuning (SFT) did not consistently reach production-acceptable levels. After SFT, the pipeline generated multiple candidates for 23,726 documents, used an automated LLM judge to score them, and retained the model’s degenerate outputs as rejected examples paired with chosen outputs. DPO reduced degeneration in every tested family, by 59.4% on average and up to 87.6%, without reducing extraction quality according to the benchmark; applicability is presented as dependent on failures being categorically identifiable, reliably scoreable, and sufficiently numerous.


### [Adding MCP Tools to Reachy Mini](https://yomu.fyi/post/adding-mcp-tools-to-reachy-mini.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Alina Lozovskaya
- Published: Jun 3, 2026
- Type: Announcement

Reachy Mini’s conversation app can now call tools hosted in public Hugging Face Spaces through MCP, allowing capabilities such as weather checks and web search to be added without editing the app or downloading tool code locally. The app retains built-in robot tools and custom local tools, while profiles use tools.txt to control which tools the model may call. The tool-spaces command validates a Space, probes its MCP endpoint, discovers tool IDs, and can append them to a selected profile; remote names are namespaced to avoid collisions. The feature supports public MCP-compatible Gradio Spaces, multiple Spaces, and backend-agnostic registration, but not private or authenticated Spaces, non-Gradio Spaces, arbitrary MCP URLs, or guaranteed parallel orchestration.


### [Holo3.1: Fast & Local Computer Use Agents](https://yomu.fyi/post/holo3-1-fast-local-computer-use-agents.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Maxime Langevin, Hamza Benchekroun, Axel Moyal, Emrick Sinitambirivoutin, Antonio Loison, Avshalom Manevich, Tony Wu, Pierre-Louis Cedoz, Aurélien Lac, Ronan Riochet
- Published: Jun 2, 2026
- Type: Announcement

Holo3.1 is a family of computer-use models released to improve robustness across web, desktop, and mobile environments, agent frameworks, and deployment targets. Based on Qwen, it adds native function-calling alongside structured JSON outputs, expands mobile automation, and offers 0.8B, 4B, 9B, and 35B-A3B sizes for different cost, latency, and performance needs. On AndroidWorld, the 35B-A3B model rises from 67% to 79.3%, while the 4B and 9B variants rise from 58% to 72%; function-calling and native execution achieve near-parity across the stated benchmarks, and Holo3.1 improves more than 25% over Holo3 in the Holotab harness. The release also provides 35B-A3B FP8, Q4 GGUF, and NVFP4 checkpoints for local inference: NVFP4 matches FP8 on OSWorld at about two points below BF16, reaches 1.74 times BF16 token throughput on DGX Spark, and with harness optimizations cuts average step time from 6.8 seconds to 3.3 seconds.


### [Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains](https://yomu.fyi/post/introducing-mellum2-a-12b-mixture-of-experts-model-by-jetbrains.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Nikita Pavlichenko
- Published: Jun 1, 2026
- Type: Announcement

JetBrains is releasing Mellum2, a 12B-parameter Mixture-of-Experts model trained from scratch on natural language and code. It targets latency-sensitive, high-throughput workloads including routing, retrieval-augmented generation (RAG), summarization, sub-agents, and coding features. The model has 12B total parameters but activates 2.5B per token, with its architecture keeping total capacity high while making inference more efficient for real-time use. Released under the Apache 2.0 license, Mellum2 is described as competitive with similarly sized open models on code generation, reasoning, science, and math benchmarks while delivering more than 2x faster inference. Its text-and-code focus supports high-throughput production workloads and private deployments where proprietary code or internal data may be involved.


### [Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic](https://yomu.fyi/post/beyond-llms-why-scalable-enterprise-ai-adoption-depends-on-agent-logic.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Nicholas Fuller
- Published: Jun 1, 2026
- Type: Explainer

Enterprise workflows are dynamic, long-running, API- and data-rich, and constrained by policies or regulations, creating challenges that an LLM alone may not handle efficiently. The article defines agent logic as software primitives—including knowledge graphs, algorithms, and program-analysis libraries—within an agent harness that steer models toward relevant workflow context. Examples span legacy COBOL and PL/1 understanding, automated test generation, incident investigation and code remediation, and compliance modernization; reported results include ~30× lower token consumption for application understanding, 20–45% higher test coverage, and up to 4.0× better incident-investigation performance than a ReAct baseline. A Condition Insights example reports 57% fewer unsupported claims and 77% lower average token usage, supporting the conclusion that structured guidance can improve quality, cost, and rule adherence.


### [Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler](https://yomu.fyi/post/profiling-in-pytorch-part-1-a-beginner-s-guide-to-torch-profiler.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Aritra Roy Gosthipaty, Sayak Paul, Sergio Paniego, Rémi Ouazan Reboul, Pedro Cuenca
- Published: May 29, 2026
- Type: Tutorial

The post introduces torch.profiler through a beginner-oriented walkthrough of profiling a matrix multiplication and addition, explaining how to configure the profiler and interpret its outputs. It uses a small function with torch.matmul and torch.add, annotates it with record\_function, captures CPU and CUDA activities after warm-up iterations, and exports a profiler table plus a Chrome trace. The table summarizes event counts and CPU or GPU time, while the trace shows execution order, call hierarchy, CPU-GPU gaps, kernel launches, and overlap. Comparing 64x64 and 4096x4096 matrices demonstrates a shift from overhead-bound behavior to compute-bound behavior; the guide also covers dispatch chains, hidden device-to-device copies, profiler buffer activity, and torch.compile's runtime and caching behavior.


### [Reachy Mini goes fully local](https://yomu.fyi/post/reachy-mini-goes-fully-local.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Amir Mahla, Andres Marafioti
- Published: May 27, 2026
- Type: Tutorial

Reachy Mini’s conversation app can now run its speech stack locally instead of sending audio to a server, avoiding cloud, API keys, and data leaving the machine. The tutorial uses speech-to-speech as a cascaded VAD → STT → LLM → TTS pipeline exposed through a Realtime API-compatible /v1/realtime WebSocket, with Silero VAD v5, Parakeet-TDT 0.6B v3, Qwen3-TTS, and a selectable LLM backend. It shows llama.cpp serving Gemma 4 E4B with parallel slots, 64k context, flash attention, and full sliding-window attention, then covers vLLM, MLX, Transformers, hosted Responses API endpoints, and network connection to a wireless robot. Once the backend and app are connected, conversations run through the local loop, while individual stages can be exchanged to trade latency, quality, language coverage, and hardware choices.


### [Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL](https://yomu.fyi/post/shipping-a-trillion-parameters-with-a-hub-bucket-delta-weight-sync-in.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Amine Dirhoussi, Quentin Gallouédec, Kashif Rasul, Lewis Tunstall, Edward Beeching, Albert Villanova del Moral, Leandro von Werra, Sergio Paniego
- Published: May 27, 2026
- Type: Problem & solution

Async RL weight synchronization currently requires the trainer to send a complete model to the inference engine after each optimizer step, creating a critical-path transfer that can reach roughly a terabyte for a frontier 1T-parameter checkpoint. The article attributes the opportunity for reduction to bf16 arithmetic: at RL learning rates, many updates fall below the bf16 visibility threshold, leaving about 99% of weights bit-identical between steps and more than 98% even in the reported worst case. TRL's delta-weight-sync implementation records changed elements around the optimizer step, encodes them in sparse safetensors, uploads each delta to a Hugging Face Bucket, and lets vLLM fetch and apply it. On Qwen3-0.6B, this reduces each per-step payload from 1.2 GB to 20–35 MB, while a demonstrated setup connected separate trainer, vLLM, and Wordle Spaces through one bucket. Open issues include extra CPU bf16 snapshots, fixed anchor cadence, and unmeasured multi-node FSDP2 support.


### [Harness, Scaffold, and the AI Agent Terms Worth Getting Right](https://yomu.fyi/post/harness-scaffold-and-the-ai-agent-terms-worth-getting-right.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Sergio Paniego, Aritra Roy Gosthipaty
- Published: May 25, 2026
- Type: Explainer

AI-agent terminology has outpaced shared definitions, leaving terms such as harness and scaffold blurred across frameworks and contexts. The glossary separates the model, which produces text but has no memory or execution loop, from scaffolding, which defines instructions, tools, output parsing, and context management, and the harness, which runs model calls, routes tool use, and decides when to stop. It presents an agent as a model plus the surrounding system that lets it act repeatedly, while distinguishing tools, skills, sub-agents, and orchestrators by their roles. For training, it defines the environment, trainer, rollout, and reward, including verifiable or learned scores and sparse or dense feedback. Because usage is not universal, the glossary offers a practical mental model rather than enforcing one vocabulary.


### [OlmoEarth v1.1: A more efficient family of Earth observation models](https://yomu.fyi/post/olmoearth-v1-1-a-more-efficient-family-of-earth-observation-models.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Kyle Wiggers
- Published: May 19, 2026
- Type: Announcement

OlmoEarth v1.1 is a new family of Earth observation models designed to reduce the compute required for large-scale satellite imagery predictions. Compute dominates the lifecycle from data export through preprocessing, inference, and post-processing, motivating a focus on transformer token sequence length. For Sentinel-2, the models collapse three resolution-specific tokens into one, reducing token counts threefold; this initially caused a 10 ppt drop on the m-eurosat kNN benchmark, so the pre-training regimen was modified. OlmoEarth v1.1 runs up to three times cheaper than v1 while maintaining similar performance across a mix of research benchmarks and partner-built tasks, although some regressions remain, and the same dataset is used to isolate methodological effects.


### [Introducing the Ettin Reranker Family](https://yomu.fyi/post/introducing-the-ettin-reranker-family.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Tom Aarsen
- Published: May 19, 2026
- Type: Announcement

Tom Aarsen introduces six Sentence Transformers CrossEncoder rerankers, ranging from 17M to 1B parameters, alongside their training data and full recipe. Each model uses an Ettin ModernBERT encoder with unpadded attention, RoPE, GeGLU, up to 8,192 tokens of context, and a modular classification head whose ablations favored CLS pooling over mean pooling. Training applies pointwise MSE distillation to scores from mixedbread-ai/mxbai-rerank-large-v2 using a broad and retrieval-focused dataset mixture. The conclusion reports state-of-the-art results at every released size, with the 400M model within 0.0024 and the 1B model within 0.0001 of the 1.54B teacher on MTEB, while all models outperform the ms-marco-MiniLM-L\*-v2 family on MTEB and NanoBEIR.


### [PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend](https://yomu.fyi/post/paddleocr-3-5-running-ocr-and-document-parsing-tasks-with-a-transforme.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: AlexZhang, cuicheng, Jun Zhang, Manhui Lin, Yue Zhang
- Published: May 18, 2026
- Type: Announcement

PaddleOCR 3.5 adds a more flexible inference-engine interface for OCR and document parsing, allowing supported models to run with a Hugging Face Transformers backend selected through engine="transformers". It keeps pipelines managed by PaddleOCR while exposing backend-specific settings such as dtype, device placement, and attention implementation through engine\_config. The release supports command-line and Python usage, with examples configuring GPU execution and float32, bfloat16, or SDPA options according to hardware and deployment environment. This provides a more natural path for RAG, Document AI, search, analytics, and agent stacks centered on PyTorch and Transformers, while the default paddle\_static backend is usually recommended when maximizing OCR or document parsing throughput is the priority.


### [Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality](https://yomu.fyi/post/granite-embedding-multilingual-r2-open-apache-2-0-multilingual-embeddi.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Radu Florian, Parul Awasthy, Aashka Trivedi, Madison Lee
- Published: May 14, 2026
- Type: Announcement

Granite Embedding Multilingual R2 introduces two Apache 2.0 multilingual embedding models built on ModernBERT: a 97M-parameter compact model and a 311M full-size model. Both cover more than 200 languages, receive enhanced retrieval training for 52 languages and nine programming languages, and support context lengths up to 32,768 tokens, compared with 512 for the R1 models. The compact model scores 60.3 on MTEB Multilingual Retrieval, while the full-size model scores 65.2; the reported results place them among the strongest open models in their parameter ranges. R2 replaces the XLM-RoBERTa architecture with alternating attention lengths, rotary position embeddings, newer multilingual and code tokenizers, and Flash Attention 2.0 support, while the 311M model adds Matryoshka embeddings and both models provide ONNX and OpenVINO weights.


[Newer posts](https://yomu.fyi/company/hugging-face/page/4.md) · [Older posts](https://yomu.fyi/company/hugging-face/page/6.md)