Researchers at Hugging Face propose Assisted Generation, an approach to improve the efficiency of text generation models. The method involves using a ...
OpenAI has developed a method to generate explanations for the behavior of individual neurons within large language models, such as GPT-4. They used G...
Hugging Face has released an early version of its coding assistant, called StarChat. The tool uses natural language processing and generation capabili...
Researchers have been experimenting with text-to-video models, which can generate videos from written descriptions. These models are based on a combin...
Researchers have introduced StarCoder, a state-of-the-art large language model (LLM) designed specifically for code. According to the developers, Star...
The Hugging Face team has released a new API for integrating their transformer models with Unity game engines. The API allows developers to use pre-tr...
Researchers have developed a method to train the popular Transformers language model using Google's TensorFlow framework on Tensor Processing Units (T...
Hugging Face's blog post discusses running the Instructify (IF) model using Hugging Face's diffusers library on a free tier Google Colab. The IF model...
Databricks and Hugging Face have collaborated on a case study that shows using their joint platform can speed up the training and tuning of Large Lang...
OpenAI has introduced new features for managing data in its ChatGPT service. Users can now opt out of having their conversation history used to improv...
Hugging Face has launched a new blog aimed at the Chinese-speaking AI community. The blog will feature articles and research on natural language proce...
Hugging Face's blog post explains how to deploy and host a Unity game on the cloud using a Space, a product that allows for easy deployment of applica...