đ Marque-pages Pinboard
â Retour Ă tous les marque-pages107 rĂ©sultats (1-107 marque-pages affichĂ©s)
medium.com
I trained an A.I. to generate British placenames The results were predictable. (Inspired in part by Janelle Shaneâs New paint colors invented by neural network. Tom Taylor did similar work in 2016 âŠ
github.com
Efficient, reusable RNNs and LSTMs for torch. Contribute to jcjohnson/torch-rnn development by creating an account on GitHub.
www.pinecone.io
A deep dive into the unification of NLP and computer vision with the Vision Transformer (ViT).
www.postgresql.org
arxiv.org
Abstract page for arXiv paper 2212.10496: Precise Zero-Shot Dense Retrieval without Relevance Labels
huggingface.co
Weâre on a journey to advance and democratize artificial intelligence through open source and open science.
github.com
Awesome list of resources about NLP applied to French | Liste de ressources liées au NLP appliqué au français - french-ai/french-nlp
www.promptingguide.ai
github.com
Structured Text Generation. Contribute to outlines-dev/outlines development by creating an account on GitHub.
github.com
A modular graph-based Retrieval-Augmented Generation (RAG) system - microsoft/graphrag
github.com
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers) - Mooler0410/LLMsPracticalGuide
huggingface.co
Discover amazing ML apps made by the community
neuml.github.io
txtai is an all-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
community.openai.com
How long should the embedding contents be? How to decide on this length. Iâm preparing the data set for embeddings Do you have any suggestions about the preparation of the data set and the contents?
blog.dottxt.co
numind.ai
Create custom machine learning models to process text automatically. Ideal for sentiment analysis, entity recognition, text classification, topic detection, content moderation, and more. No expertise required.
datasets.doctrine.fr
link.springer.com
Moral intuitions are a central motivator in human behavior. Recent work highlights the importance of moral intuitions for understanding a wide range of iss
huggingface.co
Weâre on a journey to advance and democratize artificial intelligence through open source and open science.
camembert-model.fr
Ce tutoriel a Ă©tĂ© conçu dans le cadre des journĂ©es Deep Voice de lâIRCAM par Roman CastagnĂ©, Nathan Godey et Benjamin Muller.
Une version du tutoriel en anglais en version pdf slide est disponible ici, ainsi que le mĂȘme tutoriel dans Google Colab.
Cour-de-cassation/moteurNER: communication sur le moteur de pseudonymisation de la Cour de Cassation
github.com
communication sur le moteur de pseudonymisation de la Cour de Cassation - Cour-de-cassation/moteurNER
github.com
Curated List: Practical Natural Language Processing done in Ruby - arbox/nlp-with-ruby
github.com
A minimal Python package for storing and retrieving text using chunking, embeddings, and vector search. - kagisearch/vectordb: A minimal Python package for storing and retrieving text using chunking, embeddings, and vector search.
simonwillison.net
txt.cohere.com
We take a visual approach to gain an intuition behind text embeddings, what use cases they are good for, and how they can be customized using finetuning.
www.featurebase.com
FeatureBase is a real-time database built on bitmaps. It is designed primarily for speed and horizontal scalability, and is particularly well-suited for workloads that require many real-time updates, inserts, and deletes on massive datasets.
github.com
A library for efficient similarity search and clustering of dense vectors. - Home · facebookresearch/faiss Wiki
maxhalford.github.io
Edit â I posted this on Hackernews and got some valuable feedback. Many brought up the fact that you should be able to reuse the internal state of the compressor instead of recompressing the training data each time a prediction is made. Thereâs also some insightful references to data compression theory and its ties to statistical learning
Last night I felt like reading Artificial Intelligence: A Modern Approach. I stumbled on something fun in the natural language processing chapter.
ai.stanford.edu
github.com
Label, clean and enrich text datasets with Large Language Models (LLMs) - refuel-ai/autolabel: Label, clean and enrich text datasets with Large Language Models (LLMs)
github.com
Explore large language models on any computer with 512MB of RAM - jncraton/languagemodels: Explore large language models on any computer with 512MB of RAM
simonwillison.net
factba.se
The complete collection of Joe Biden interviews, speeches, tweets from twitter (including deleted tweets) and more. Bias-free. Skip the spin. Instantly access everything Joe Biden has said on a particular topic or person.
www.thisworddoesnotexist.com
This Word Does Not Exist uses an artificial intelligence model named GPT-2 to invent new English words.
textsynth.com
github.com
1 line for thousands of State of The Art NLP models in hundreds of languages The fastest and most accurate way to solve text problems. - JohnSnowLabs/nlu: 1 line for thousands of State of The Art NLP models in hundreds of languages The fastest and most accurate way to solve text problems.
newscatcherapi.com
Annotation is the part where most projects stall, and it can make or break your models. Here are some tools and tips to help you with text annotation needs.
huggingface.co
Weâre on a journey to advance and democratize artificial intelligence through open source and open science.
github.com
A list of totally open alternatives to ChatGPT. Contribute to nichtdax/awesome-totally-open-chatgpt development by creating an account on GitHub.
www.gnod.com
Compare search results across multiple search engines
github.com
Adding guardrails to large language models. Contribute to ShreyaR/guardrails development by creating an account on GitHub.
github.com
Tensor search for humans. Contribute to marqo-ai/marqo development by creating an account on GitHub.
rom1504.medium.com
We live in a world with an explosion of information. There are millions of clothes, songs, movies, recipes, cars, houses, which one should you pick? Semantic search can find the right one for anyâŠ
openai.com
huggingface.co
nlpcloud.com
Text understanding / text generation (NLP) API, for NER, sentiment analysis, emotion analysis, text classification, summarization, dialogue summarization, question answering, text generation, image generation, translation, language detection, grammar and spelling correction, intent classification, paraphrasing and rewriting, code generation, chatbot/conversational AI, blog post generation, product description and ad generation, automatic speech recognition api, speech to text, semantic similarity, semantic search, Part-Of-Speech tagging, tokenization, lemmatization, and embeddings. Fine-tune and deploy your own AI models. No DevOps required.
github.com
The simplest, fastest repository for training/finetuning medium-sized GPTs. - karpathy/nanoGPT: The simplest, fastest repository for training/finetuning medium-sized GPTs.
smartynames.com
Finding a creative and unique domain that is still available is easy with SmartyNames.com | Tell us what you do, and our robots will find the domain that is just right for you. Company name generator in one click.
deepimagination.cc
huggingface.co
Weâre on a journey to advance and democratize artificial intelligence through open source and open science.
github.com
Text generator is a handy plugin for Obsidian that helps you generate text content using GPT-3 (OpenAI). - GitHub - nhaouari/obsidian-textgenerator-plugin: Text generator is a handy plugin for Obsidian that helps you generate text content using GPT-3 (OpenAI).
felixkreuk.github.io
github.com
Just the facts -- web page content extraction. Contribute to dragnet-org/dragnet development by creating an account on GitHub.
github.com
Python port of Boilerpipe library. Contribute to jmriebold/BoilerPy3 development by creating an account on GitHub.
github.com
A Python 3 compatible version of goose http://goose3.readthedocs.io/en/latest/index.html - goose3/goose3: A Python 3 compatible version of goose http://goose3.readthedocs.io/en/latest/index.html
github.com
Python interface to Boilerpipe, Boilerplate Removal and Fulltext Extraction from HTML pages - misja/python-boilerpipe: Python interface to Boilerpipe, Boilerplate Removal and Fulltext Extraction from HTML pages
github.com
Heuristic based boilerplate removal tool. Contribute to miso-belica/jusText development by creating an account on GitHub.
www.oncrawl.com
SEO Crawler and Log Analyzer for Technical SEO audits. Bridge technical SEO with machine learning and data science for increased revenues
openai.com
en.wikipedia.org
transformersbook.com
nlpparis.wordpress.com
github.com
LexNLP by LexPredict. Contribute to LexPredict/lexpredict-lexnlp development by creating an account on GitHub.
github.com
Pretrained language model with 100B parameters. Contribute to yandex/YaLM-100B development by creating an account on GitHub.
cemantix.herokuapp.com
Trouvez le mot secret en essayant de vous en approcher le plus possible sémantiquement !
semantle.com
www.textrazor.com
TextRazor is the world's fastest and most accurate Natural Language Processing API
www.sciencedirect.com
www.eleuther.ai
andrewmayneblog.wordpress.com
www.ai21.com
predictice.com
projector.tensorflow.org
umap-learn.readthedocs.io
fr.wikipedia.org
fr.wikipedia.org
commoncrawl.org
www.nltk.org
en.wikipedia.org
web.stanford.edu
academictorrents.com
louismartin.eu
www.technologyreview.com
radimrehurek.com
fr.wikipedia.org
fr.wiktionary.org
aws.amazon.com
huggingface.co
Build, train and deploy state of the art models powered by the reference open source in natural language processing.