AI
Introducing text and code embeddings
OpenAI has introduced a new endpoint called embeddings in its API. This feature allows users to perform various text and code-related tasks such as se...
AI
AI
Supercharged Searching on the 🤗 Hub
The Hugging Face team has introduced a new search feature to their model hub, allowing users to quickly find and explore models, datasets, and tasks. ...
AI
Text and code embeddings by contrastive pre-training
OpenAI has developed a method to create embeddings for both text and code using contrastive pre-training. This approach combines natural language proc...
AI
Welcome Stable-baselines3 to the Hugging Face Hub 🤗
Hugging Face has added a popular deep reinforcement learning library called Stable-baselines3 (SB3) to its model hub. SB3 is designed for training age...
AI
Case Study: Millisecond Latency using Hugging Face Infinity and modern CPUs
Researchers at Hugging Face achieved millisecond latency in a model serving environment using their Infinity library and modern CPUs. They compared th...
AI
Boosting Wav2Vec2 with n-grams in 🤗 Transformers
Researchers have found a way to improve the performance of Wav2Vec2, a popular speech recognition model. They achieved this by incorporating n-grams i...
AI
Deploy GPT-J 6B for inference using Hugging Face Transformers and Amazon SageMaker
Hugging Face has published a blog post on how to deploy the GPT-J 6B model for inference using Hugging Face Transformers and Amazon SageMaker. The pos...
AI
Active Learning with AutoNLP and Prodigy
Hugging Face, a popular AI research platform, has introduced two new tools to simplify the process of training natural language processing (NLP) model...
AI
Gradio is joining Hugging Face!
Gradio, an open-source library for building and sharing machine learning models, has joined forces with Hugging Face. The move allows Gradio to levera...
AI
WebGPT: Improving the factual accuracy of language models through web browsing
Researchers at OpenAI have improved the factual accuracy of language models by fine-tuning GPT-3 with a text-based web browser. This allows the model ...
AI
Perceiver IO: a scalable, fully-attentional model that works on any modality
Perceiver IO is an AI model designed to handle multiple types of data, including images, audio, and text. It uses a fully-attentional approach, which ...
AI
Customizing GPT-3 for your application
OpenAI's GPT-3 language model can be customized for specific applications using a single command. This allows developers to tailor the model's output ...