This official Hugging Face blog post systematically maps out the complete ecosystem it has built around open-source large language models (LLMs). As…
In the era of booming generative AI, fine-tuning large image generation models like Stable Diffusion has generally been considered the exclusive domain of…
This official Hugging Face blog post explores in depth how to use the Transformers.js library to run machine learning (ML) models directly in the browser…
This official Hugging Face blog post introduces how to use their hosted service "Inference Endpoints" to deploy large language models (LLMs). With the rapid…
This Hugging Face blog post details how to use open-source machine learning models to build a "Text-to-Web-App" generator. With the breakthroughs large…
The Hugging Face Ethics and Society team has published the fourth edition of its newsletter, this time focusing on the problem of "bias" in text-to-image (T2I)…
### Background: The Gap Between Leaderboard Scores and Paper Results By mid-2023, Hugging Face's Open LLM Leaderboard had become the community's go-to platform…
Hugging Face submitted a formal response to the Request for Comment (RFC) on "AI Accountability" initiated by the U.S. Department of Commerce's National…
In the era of rapidly advancing generative AI, deploying large deep learning models to users' personal devices (edge devices) has long been a major challenge…
In June 2023, Hugging Face officially announced a long-term strategic partnership with chip giant AMD. The core objective of this collaboration is to optimize…
In the development of large language models (LLMs), RLHF (Reinforcement Learning from Human Feedback) is the critical step for aligning models with human…
Hugging Face has published a practical guide specifically for the GLAM sector (Galleries, Libraries, Archives, and Museums), exploring how cultural heritage…
The Falcon series of large language models (including Falcon-40B and Falcon-7B), developed by Abu Dhabi's Technology Innovation Institute (TII), have…
Hugging Face and AWS have jointly announced the new "Hugging Face LLM Inference Container" — a brand-new deep learning container (DLC) purpose-built for Amazon…
The popular open-source topic modeling tool BERTopic has announced a deep integration with Hugging Face Hub. This update brings tremendous convenience to NLP…
This technical blog post from Replicate explores how to go beyond traditional prompt engineering and model fine-tuning, using "Logits Processing" to precisely…
This official Hugging Face blog post introduces a deep integration with the `bitsandbytes` library, formally adding 4-bit quantization support to…
Hugging Face has announced an important partnership with Microsoft, officially launching the "Hugging Face Model Catalog" on the Azure Machine Learning (Azure…
Hugging Face and IBM have officially announced a partnership to collaborate deeply on IBM's newly launched watsonx.ai platform. watsonx.ai is IBM's…
This Hugging Face blog post provides an in-depth exploration of how to use InstructPix2Pix technology to apply instruction tuning to Stable Diffusion, enabling…
In May 2023, Hugging Face announced that its new weight storage format for deep learning models, "Safetensors," had successfully passed an independent security…
This technical blog post from Hugging Face takes an in-depth look at the challenges the BigCode project (the collaborative initiative behind StarCoder) faced…
This article introduces the latest outcome of a collaboration between Hugging Face and Intel: "Q8-Chat," a project designed to demonstrate how to efficiently…
This blog post from Hugging Face provides a detailed walkthrough of how to deploy and run an open-source ChatGPT-like chatbot on a single AMD GPU using AMD's…
France's Commission Nationale de l'Informatique et des Libertés (CNIL — France's personal data protection authority) has announced that it has selected Hugging…
Hugging Face has announced official support for RWKV (Receptive Weighted Key Value) models in its `transformers` library. RWKV is an innovative architecture…
Large language models (LLMs) typically generate text using an "autoregressive" mechanism, meaning the model must generate one token at a time. Each generation…
Hugging Face has announced the launch of StarChat Alpha, a conversational AI assistant designed specifically for programming. The model is based on StarCoder…
The BigCode community project, led jointly by Hugging Face and ServiceNow, has officially released StarCoder (along with its base version, StarCoderBase) — a…
This technical guide from Hugging Face provides a detailed walkthrough of how to efficiently train language models by combining TensorFlow, the Hugging Face…