Tag

#nlp

Every item tagged nlp, newest first.

21 items

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

Hugging Face released Tokenization in Transformers v5, which simplifies and modularizes tokenization. The update aims to make tokenization more accessible and easier to use. This change can help builders working with Transformers to improve their workflow and model performance. The new version provides a clearer and more modular approach to tokenization.

Key takeaways

Simpler and more modular tokenization
Easier to use and integrate
Improved accessibility for builders

HHugging Face Blog#tokenization #transformers #nlp

productsOct 22

Sentence Transformers is joining Hugging Face!

Sentence Transformers is joining Hugging Face, expanding the range of natural language processing tools available on the platform. This move is expected to enhance the capabilities of Hugging Face's offerings. As a result, developers can anticipate more comprehensive and integrated solutions for their NLP tasks. The integration aims to simplify the workflow for builders using Sentence Transformers and Hugging Face products.

Key takeaways

Sentence Transformers joins Hugging Face
Expanded NLP capabilities on Hugging Face platform
Simplified workflow for developers

HHugging Face Blog#nlp #integration #machine-learning

toolsJul 1

Training and Finetuning Sparse Embedding Models with Sentence Transformers

The Hugging Face Transformers library now supports sparse embedding models through Sentence Transformers. You can train and fine-tune sparse models using the library's API. Sparse embedding models can be more efficient and scalable for certain NLP tasks. This update enables builders to experiment with sparse models for their specific use cases.

Key takeaways

Hugging Face Transformers supports sparse embedding models via Sentence Transformers.
Sparse models can be more efficient for certain NLP tasks.
Builders can train and fine-tune sparse models using the library's API.

HHugging Face Blog#sparse-embeddings #sentence-transformers #nlp

otherJun 5

Introducing NPC-Playground, a 3D playground to interact with LLM-powered NPCs

Hugging Face released NPC-Playground, a 3D playground for interacting with LLM-powered NPCs. The playground is built on top of Hugging Face's Transformers library and allows users to create and customize their own NPCs. This can be used for various applications such as games, simulations, and more.

Key takeaways

3D playground for interacting with LLM-powered NPCs
LLM-powered NPCs can be used for various applications such as games, simulations, and more
The playground is built on top of Hugging Face's Transformers library and allows users to create and customize their own NPCs

HHugging Face Blog#nlp #ai-research #hugging-face

tutorialsMay 28

Training and Finetuning Embedding Models with Sentence Transformers

Hugging Face released a guide on training and fine-tuning embedding models with sentence transformers. The guide covers the basics of sentence transformers and provides a step-by-step tutorial on how to train and fine-tune these models. This resource is useful for builders who want to improve the performance of their natural language processing applications. By fine-tuning pre-trained models, developers can adapt them to specific tasks and domains.

Key takeaways

Hugging Face provides a guide on training sentence transformers.
Fine-tuning pre-trained models can improve performance on specific tasks.
Sentence transformers can be used for various NLP applications.

HHugging Face Blog#nlp #sentence-transformers #fine-tuning

modelsApr 11

Vision Language Models Explained

Hugging Face published an article explaining vision language models, which combine computer vision and natural language processing to enable tasks like image captioning and visual question answering. These models can be fine-tuned for specific applications. Builders can use vision language models to develop more accurate and informative image-based interfaces. The article provides an overview of the technology and its potential use cases.

Key takeaways

Vision language models integrate computer vision and NLP.
Enable tasks like image captioning and visual question answering.
Can be fine-tuned for specific applications.

HHugging Face Blog#vision-language-models #nlp #computer-vision

toolsApr 4

Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B

Hugging Face has integrated Motherduck's DuckDB-NSQL-7B model with their Dataset Viewer API, enabling Text2SQL capabilities. This integration allows users to query databases using natural language. The DuckDB-NSQL-7B model is a 7B parameter model fine-tuned for SQL generation tasks. You can use this integration to build applications that generate SQL queries from text inputs.

Key takeaways

DuckDB-NSQL-7B model integrated with Hugging Face Dataset Viewer API
Text2SQL capabilities enabled through natural language querying
7B parameter model fine-tuned for SQL generation tasks

HHugging Face Blog#text2sql #dataset-viewer #nlp

tutorialsMar 22

Total noob’s intro to Hugging Face Transformers

Hugging Face provides an introduction to transformers for beginners, covering the basics of transformer models and their applications. The guide is designed for those new to the field, aiming to make the technology more accessible. You can learn about the fundamentals of transformers and how they are used in various tasks. This resource is useful for builders who want to get started with transformer-based projects.

Key takeaways

Introduction to transformer models for beginners
Covers basics and applications of transformers
Resource for builders starting with transformer-based projects

HHugging Face Blog#transformers #beginner-friendly #nlp

modelsAug 9

Optimizing Bark using 🤗 Transformers

Hugging Face optimized the Bark model using their Transformers library, achieving improved performance. The optimization process involved fine-tuning the model on a specific task, resulting in better accuracy and efficiency. This optimization is notable for builders working with Bark, as it can lead to improved results in their applications. The optimization is detailed in a blog post on the Hugging Face website.

Key takeaways

Bark model optimized using Hugging Face Transformers
Improved performance through fine-tuning
Optimization details available in Hugging Face blog post

HHugging Face Blog#model-optimization #transformers #nlp

otherJun 22

Panel on Hugging Face

A panel discussion was held on Hugging Face, covering various topics related to the platform and its ecosystem. The discussion likely involved the company's products and services, such as its popular transformers library and model hub. As a builder, you may be interested in learning about the latest developments and insights from the Hugging Face community. The panel may have also touched on the company's future plans and roadmap.

Key takeaways

Hugging Face panel discussion held
Transformers library and model hub likely discussed
Company's future plans and roadmap may have been shared

HHugging Face Blog#nlp #machine-learning #community

researchFeb 3

A Dive into Vision-Language Models

Hugging Face published a blog post exploring vision-language models, which combine computer vision and natural language processing to enable tasks like image captioning and visual question answering. These models have many potential applications, including image search and generation. You can use them to build more intuitive interfaces and improve user experience. Vision-language models are an active area of research, with new architectures and techniques being developed regularly.

Key takeaways

Vision-language models combine computer vision and NLP for tasks like image captioning.
These models have applications in image search, generation, and more.
New architectures and techniques are being developed for vision-language models.

HHugging Face Blog#vision-language-models #nlp #computer-vision

researchNov 21

Accelerating Document AI

Hugging Face has introduced Accelerating Document AI, a new initiative focused on improving document-related AI tasks. This effort aims to enhance the performance and efficiency of document processing models. As a result, developers can expect better outcomes when working with documents, such as more accurate text extraction and improved layout analysis. The initiative is likely to impact the development of document-centric applications and services.

Key takeaways

Improved document processing model performance
Enhanced text extraction accuracy
Better layout analysis capabilities

HHugging Face Blog#document-ai #nlp #efficiency

toolsAug 22

Pre-Train BERT with Hugging Face Transformers and Habana Gaudi

Hugging Face and Habana collaborated on pre-training BERT using Habana Gaudi hardware. This allows developers to fine-tune BERT models on specific tasks and datasets. The pre-training process can be done using Hugging Face Transformers. This collaboration enables faster and more efficient training of BERT models. You can use the pre-trained models for various natural language processing tasks.

Key takeaways

Pre-trained BERT models available for fine-tuning
Habana Gaudi hardware used for pre-training
Faster training times with Hugging Face Transformers

HHugging Face Blog#pre-training #transformers #nlp

tutorialsAug 10

Train and Fine-Tune Sentence Transformers Models

Hugging Face provides a guide on training and fine-tuning sentence transformers models. The process involves preparing a dataset, creating a custom dataset class, and using the transformers library to train a model. Fine-tuning a pre-trained model can improve performance on specific tasks. You can use this approach to adapt models to your particular use case.

Key takeaways

Train sentence transformers models from scratch or fine-tune pre-trained models.
Use the transformers library to simplify the training process.
Fine-tuning can improve model performance on specific tasks.

HHugging Face Blog#sentence-transformers #fine-tuning #nlp

tutorialsJun 23

Getting Started With Embeddings

Hugging Face published a guide on getting started with embeddings, covering the basics and applications of embeddings in natural language processing. The guide is intended for developers and researchers who want to learn about embeddings and how to use them in their projects. Embeddings are a fundamental concept in NLP and are used in many state-of-the-art models. By understanding embeddings, you can improve your NLP models and applications.

Key takeaways

Embeddings are a fundamental concept in NLP.
Hugging Face provides a guide for getting started with embeddings.
Embeddings are used in many state-of-the-art NLP models.

HHugging Face Blog#nlp #embeddings #tutorials

modelsMar 2

BERT 101 - State Of The Art NLP Model Explained

The BERT 101 article explains the state of the art NLP model BERT, its architecture, and its applications. BERT is a pre-trained language model that achieved state-of-the-art results on various NLP tasks. You can use BERT for tasks such as sentiment analysis, question answering, and text classification. The article provides an overview of BERT's capabilities and its potential use cases.

Key takeaways

BERT is a pre-trained language model with state-of-the-art results on NLP tasks.
BERT can be fine-tuned for specific tasks such as sentiment analysis and question answering.
BERT is widely used in various NLP applications.

HHugging Face Blog#nlp #pre-trained-models #language-models

toolsJan 12

Boosting Wav2Vec2 with n-grams in 🤗 Transformers

The Hugging Face Transformers library now supports boosting Wav2Vec2 with n-grams, allowing for improved speech recognition performance. This update enables developers to leverage n-gram techniques to enhance the accuracy of their speech recognition models. By incorporating n-grams, Wav2Vec2 can better capture contextual relationships in audio data. This can be particularly useful for builders working on speech-to-text applications.

Key takeaways

Wav2Vec2 now supports n-gram boosting in Hugging Face Transformers.
N-grams can improve speech recognition performance by capturing contextual relationships.
Enhanced accuracy can benefit speech-to-text applications.

HHugging Face Blog#speech-recognition #nlp #transformers

toolsJul 13

Welcome spaCy to the Hugging Face Hub

SpaCy is now available on the Hugging Face Hub, allowing users to easily download and use spaCy models. This integration provides access to a wide range of pre-trained models for natural language processing tasks. You can now use spaCy models in your applications with the Hugging Face ecosystem. The addition of spaCy expands the Hub's offerings for NLP tasks.

Key takeaways

SpaCy models available on Hugging Face Hub
Pre-trained models for various NLP tasks
Easy integration with Hugging Face ecosystem

HHugging Face Blog#nlp #natural-language-processing #model-hub

toolsJun 28

Sentence Transformers in the Hugging Face Hub

Hugging Face has introduced sentence transformers in the Hugging Face Hub, allowing users to easily access and utilize these models for various natural language processing tasks. Sentence transformers are particularly useful for tasks such as semantic search, question answering, and text classification. The integration provides a convenient way for developers to leverage these models in their applications. This addition expands the range of tools available in the Hugging Face Hub for NLP tasks.

Key takeaways

Sentence transformers available in the Hugging Face Hub
Supports tasks like semantic search and question answering
Convenient access for developers to leverage these models

HHugging Face Blog#nlp #transformers #hugging-face-hub

toolsNov 3

Porting fairseq wmt19 translation system to transformers

The fairseq wmt19 translation system has been ported to the transformers library, allowing for easier integration and use of the system. This port enables developers to leverage the strengths of both fairseq and transformers. The ported system can be used for machine translation tasks, providing a more accessible solution for builders. The port is available on the Hugging Face model hub.

Key takeaways

Fairseq wmt19 translation system ported to transformers library.
Easier integration with other transformers models and tools.
Available on Hugging Face model hub for use in machine translation tasks.

HHugging Face Blog#machine-translation #nlp #porting

modelsJul 3

The Reformer - Pushing the limits of language modeling

Hugging Face introduced the Reformer, a language model designed to push the limits of language understanding. The Reformer aims to improve upon existing models by increasing efficiency and reducing computational costs. This development is notable for builders as it may lead to more accessible and affordable language modeling solutions. The Reformer's capabilities and potential applications are being explored by the Hugging Face community.

Key takeaways

Reformer model introduced by Hugging Face
Aims to improve efficiency and reduce computational costs
Potential for more accessible language modeling solutions

HHugging Face Blog#language-modeling #efficiency #nlp