lag-llama
spark-nlp-workshop
lag-llama | spark-nlp-workshop | |
---|---|---|
2 | 16 | |
1,051 | 1,011 | |
8.5% | 1.4% | |
8.4 | 9.6 | |
7 days ago | 3 days ago | |
Python | Jupyter Notebook | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
lag-llama
spark-nlp-workshop
- FLaNK Stack Weekly 19 Feb 2024
-
Spark-NLP 4.1.0 Released: Vision Transformer (ViT) is here! The very first Computer Vision pipeline for the state-of-the-art Image Classification task, AWS Graviton/ARM64 support, new EMR & Databricks support, 1000+ state-of-the-art models, and more!
You can visit Spark NLP Workshop for 100+ examples
-
Spark-NLP 4.0.0 🚀: New modern extractive Question answering (QA) annotators for ALBERT, BERT, DistilBERT, DeBERTa, RoBERTa, Longformer, and XLM-RoBERTa, official support for Apple silicon M1, support oneDNN to improve CPU up to 97%, improved transformers on GPU up to +700%, 1000+ SOTA models
I submitted a pull request here: https://github.com/JohnSnowLabs/spark-nlp-workshop/pull/552 that I think addresses both of those.
-
How AI is used for mental health therapy
In SnowLab’s implementation, for example, they wrote a search function called get_clinical_entities that finds all mentions of medications for 100 patients, as well as specifications, if any, about the quantity and frequency the medication is consumed. The location of the sentence in the overall piece is also recorded, to locate the information easier.
-
John Snow Labs Spark-NLP 3.4.0: New OpenAI GPT-2, new ALBERT, XLNet, RoBERTa, XLM-RoBERTa, and Longformer for Sequence Classification, support for Spark 3.2, new distributed Word2Vec, extend support to more Databricks & EMR runtimes, new state-of-the-art transformer models, bug fixes, and lots more!
There are so many examples here for Python users (I would start from tutorials/Certificate_Trainings): https://github.com/JohnSnowLabs/spark-nlp-workshop
-
John Snow Labs Spark-NLP 3.1.0: Over 2600+ new models and pipelines in 200+ languages, new DistilBERT, RoBERTa, and XLM-RoBERTa transformers, support for external Transformers, and lots more!
Spark NLP Workshop notebooks
-
Release John Snow Labs Spark-NLP 2.7.0: New T5 and MarianMT seq2seq transformers, detect up to 375 languages, word segmentation, over 720+ models and pipelines, support for 192+ languages, and many more! · JohnSnowLabs/spark-nlp
Spark NLP training certification notebooks for Google Colab and Databricks
Spark NLP training certification notebooks for Google Colab and Databricks
Spark NLP training certification notebooks for Google Colab and Databricks
Spark NLP training certification notebooks for Google Colab and Databricks
What are some alternatives?
llmware - Unified framework for building enterprise RAG pipelines with small, specialized models
spark-nlp - State of the Art Natural Language Processing
sent - a simple plaintext presentation tool
spark-nlp-display - A library for the simple visualization of different types of Spark NLP annotations.
nifi - Apache NiFi
dstack - An open-source container orchestration engine for running AI workloads in any cloud or data center. https://discord.gg/u8SmfwPpMd
inox - 🛡️ A secure web development platform and programming language.
proton - A streaming SQL engine, a fast and lightweight alternative to ksqlDB and Apache Flink, 🚀 powered by ClickHouse.
TensorRT-LLM - TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
magika - Detect file content types with deep learning