AI BriefingHuggingFace Blog news
The latest AI and developer news from HuggingFace Blog, with short summaries.
Visit website →fastai adds official Hugging Face Hub integration
fastai users can now upload and share their models on the Hugging Face Hub with just a single line of code.
Leveraging PyTorch FSDP with Accelerate
This introduces how to accelerate large-scale model training by leveraging PyTorch FSDP through Hugging Face's Accelerate library.
Hugging Face Carbon Emissions Tracking
Hugging Face has introduced a feature to track and search CO2 emissions generated during model training and deployment.
Habana Labs and Hugging Face Partner to Accelerate Transformer Training
The integration of Habana Labs' SynapseAI and Hugging Face's Optimum library accelerates Transformer training based on Gaudi processors.
Hugging Face's Design Philosophy for Transformers
It explains why Hugging Face adopted a 'single model file' policy instead of the DRY principle when designing the Transformers library.
Hugging Face Integrates the Decision Transformer Library
Hugging Face has integrated Decision Transformer, an offline reinforcement learning model, into the transformers library.
Accelerating BERT Inference with AWS Inferentia
A guide to optimizing BERT model inference performance and reducing costs using AWS Inferentia and Hugging Face Transformers.
Transformers Enhances Text Generation Control Features
It introduces the Constrained Beam Search feature in the Transformers library, which controls text generation to include specific words.
Implementing ASR for Long Audio Files with Wav2Vec2
This explains how to leverage the characteristics of the CTC architecture to perform high-quality speech recognition on long audio files without memory issues.
Stable-baselines3 Integrated with Hugging Face Hub
The reinforcement learning library Stable-baselines3 is now available on the Hugging Face Hub.
Combining Wav2Vec2 with an n-gram Language Model
This provides a technical guide on improving Wav2Vec2's speech recognition performance using an n-gram language model.
Hugging Face Announces Acquisition of Gradio
Hugging Face has acquired Gradio, a tool for building machine learning demos.
HuggingFace adds support for Perceiver IO
Perceiver IO, a scalable multimodal model that can process any kind of data, has been added to the Transformers library.
CodeParrot: Training a Code Model
This introduces the dataset construction and training methodology behind CodeParrot, a Python code generation model released by HuggingFace.
Hugging Face Supports the ML-Agents Ecosystem
Hugging Face has announced the building of a Deep Reinforcement Learning (DRL) ecosystem using Unity ML-Agents.
Hugging Face Releases DMT for Dataset Analysis
The Data Measurements Tool, an open-source tool for measuring and comparing dataset quality, has been released.
Guide to Fine-tuning Multilingual ASR Based on XLS-R
This explains a fine-tuning method that uses Hugging Face's XLS-R model to improve speech recognition (ASR) performance for low-resource languages.
Guide to Optimizing BERT Inference on Intel CPUs
It explains how to optimize BERT model inference performance by leveraging the hardware and software features of Intel Xeon CPUs.
Hugging Face Unveils Advanced NLP Course and Community Event
Hugging Face announced the release of Course Part 2 for in-depth NLP learning along with a community event.
Training Sentence Embeddings on 1 Billion Data Pairs
This introduces a technical methodology for building an SOTA-level sentence embedding model using 1 billion training pairs and JAX/Flax.