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 solo student developer launched Souva, a free app that turns photos of a user's fridge and pantry into recipes using AI, with photo scans costing about $0.002 each and capped at 3 per day, and AI ge…
A user reports being unable to download models from Hugging Face in Google Colab, with downloads stuck at 1% for both embedding models and LLMs, despite attempting fixes like disabling HF_HUB_DISABLE_…
Google and a broad set of industry partners including Microsoft, GitHub, Hugging Face, Cisco, Databricks, GoDaddy, NVIDIA, Salesforce, ServiceNow, and Snowflake published Agentic Resource Discovery (A…
A developer reports that DPO training using Hugging Face's DPOTrainer on a fine-tuned T5 model causes the model to generate repetitive outputs (e.g., 'a a a a a a') and degrade conversational coherenc…
Chinese open-weight models accounted for 41% of downloads on Hugging Face this spring, surpassing U.S. models, and the top six most popular models on OpenRouter are all open models from Chinese firms …
Google and industry partners including Microsoft, GitHub, Hugging Face, Cisco, Databricks, GoDaddy, NVIDIA, Salesforce, ServiceNow, and Snowflake announced the Agentic Resource Discovery (ARD) Specifi…
An independent developer built a pipeline where an AI agent uses reinforcement learning (RL) to train smaller models via RL, achieving a peak reward of ~0.63 over 54 training steps and transferring to…
A developer claims that fusing three small local language models at the logit level on a laptop can match the reasoning of Anthropic's Fable 5, avoiding the cost and latency of centralized APIs. The t…
A developer built a sarcastic AI code reviewer using HTML, CSS, and the open-source Qwen2.5-Coder-7B-Instruct model from Hugging Face. The tool roasts bad markup and praises semantic HTML with dry sar…
Open-source coding agents can now run entirely on local consumer hardware such as a 2020-era NVIDIA RTX 3090, eliminating usage-based pricing from AI vendors. The setup uses a quantized Gemma4 model s…
A developer quantized Google's MedGemma-1.5-4B medical vision-language model to INT4 (W4A16) using llm-compressor's GPTQModifier, reducing size from 8.6 GB to 5.2 GB for self-hosted deployment. The pr…
Hugging Face's Dataset Viewer API is returning a 503 Service Temporarily Unavailable error for all datasets, as reported by a user testing the endpoint https://datasets-server.huggingface.co/is-valid?…
A user reports a runtime error on Hugging Face's platform, with the interface displaying 'Unable to Schedule — Not enough hardware capacity,' causing the app to get stuck in an endless 'Starting...' l…
Researchers have developed modelDNA, a tool that verifies the lineage of open-weight large language models by fingerprinting a model from roughly 100-300 MB of ranged HTTP reads and comparing it again…
Users report that Hugging Chat is not working on mobile phones, with the 'Get Started' button unresponsive. A related discussion thread on Hugging Face forums confirms the issue, and affected users ar…
A Hugging Face forum user reported the service being down on July 14, 2026, but the topic was deleted by the author. Related discussions include errors in the Hub API and documentation page outages.…
Chinese AI models from DeepSeek, MiniMax, Tencent, and Xiaomi have seized OpenRouter's top five positions, offering 4–8x cost advantages over comparable US models and triggering real production migrat…
A model download from Hugging Face freezes at a specific percentage due to a bug in the Xet-aware fetch/reconstruction path, according to a Colab experiment by a user. The issue, reproducible with the…
Hugging Face users are reporting an 'Access Denied' error when attempting to download any model, including open-weight models previously accessible. Multiple users on the Hugging Face forum confirm th…
Robbyant released six embodied-AI models over four days spanning perception, action, world modeling and video, positioning the LingBot stack as a platform for robotics developers. The public artifacts…