Hugging Face is an AI community platform and company providing a hub for open-source machine learning models, datasets, and demo spaces. It hosts over 500,000 models and is widely used by the AI research community.
A new tutorial demonstrates how to build a text clustering pipeline using large language model embeddings and the HDBSCAN algorithm to automatically discover topics in unlabeled text data. The pipelin…
Baidu released Unlimited-OCR, a one-shot long-horizon parsing model that extends DeepSeek-OCR, on June 22, 2026. The open-source model supports single-image and multi-page PDF parsing with configurabl…
A Hugging Face user whose account was locked after duplicating a Space reports that the account was eventually restored after contacting safety@huggingface.co and HF Discord. The user advises others n…
Gradio web components are failing to load on Hugging Face Spaces due to a host resolution issue, generating malformed URLs like 'https://.hf.space/config' instead of valid Space subdomains. The proble…
Intel's AutoRound quantization algorithm for large language models claims state-of-the-art performance, enabling LLMs like Qwen 3.6 to run on consumer GPUs. In testing, AutoRound produced consistent o…
Hugging Face automated its weekly huggingface_hub releases using a GitHub Actions workflow with open-source tools and open-weights AI models, keeping a human in the loop for release notes and announce…
Google Chrome engineer Thomas Steiner is experimenting with the proposed Cross-Origin Storage API to enable Transformers.js models to be shared across different origins, reducing redundant downloads a…
Developer Simon Willison ported the Moebius 0.2B image inpainting model to run in a browser using WebGPU, bypassing the original requirement for PyTorch and NVIDIA CUDA. The project, completed with as…
Unsloth released a guide on June 18 to run Z.ai's 744-billion-parameter GLM-5.2 model on local hardware using aggressive quantization, compressing the model from 1.51 TB to as low as 217 GB. The tooli…
Business leaders and a psychiatrist at VivaTech in Paris argued that AI is increasing workplace stress by adding new demands, fueling uncertainty, and challenging workers' sense of purpose. A Headspac…
Baidu released PP-OCRv6, a family of OCR models scaling from 1.5M to 34.5M parameters, supporting 50 languages. The medium model achieves 86.2% detection Hmean and 83.2% recognition accuracy, improvin…
NLTK remains a viable tool for advanced text preprocessing despite the rise of LLMs. Three key tricks—MWETokenizer for preserving multi-word expressions, POS-aware lemmatization, and statistical collo…
Three recent AI events reveal the fragility of relying on third-party model APIs. Anthropic suspended access to its Fable 5 and Mythos 5 models after a US government export control directive, causing …
A user reported that their Hugging Face Space 'kayinda/rxsteward' was stuck in a 'Building' state and could not be deleted via the web UI or API due to a 403 error. Hugging Face staff member hysts con…
Hugging Face fixed a UI synchronization glitch that caused Spaces to show a 'Starting' status instead of 'Running'. The bug was a frontend latency issue requiring no backend changes, and services are …
A new open-source tool called Trace Commons allows developers to donate anonymized traces from coding-agent sessions to a CC-BY-4.0 dataset on Hugging Face, aiming to make reasoning data from tools li…
CSGHub, an open-source platform for managing Large Language Model (LLM) assets, offers on-premise deployment for secure, offline operation. It provides a unified interface for uploading, downloading, …
Moonshot AI released Kimi K2.7 Code, a 1-trillion-parameter open-source coding model that uses 30% fewer reasoning tokens than its predecessor and outperforms Claude Opus 4.8 on MCP tool-calling bench…
Z.ai released GLM-5.2, an open-source AI model with full weights on Hugging Face under an MIT license, on June 16. The model outperforms GPT-5.5 on the SWE-bench Pro benchmark with a score of 62.1 ver…
A Hugging Face Space by user anandkr has been stuck in a 'Restarting' state for over 16 hours, failing to serve traffic from new builds despite successful container startups. The issue persists across…