nlu
simpletransformers
| nlu | simpletransformers | |
|---|---|---|
| 25 | 6 | |
| 809 | 3,984 | |
| 0.9% | - | |
| 8.6 | 7.3 | |
| 11 days ago | about 1 month ago | |
| Python | Python | |
| 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.
nlu
-
1 line to visualizations for dependency trees, entity relationships, resolution, assertion, NER and new models for Afrikaans, Welsh, Maltese, Tamil, and Vietnamese - John Snow Labs NLU 3.0.1 for Python
See the visualization tutorial notebook and visualization docs for more info.
All of the 140+ NLU tutorial Notebooks have been updated and reworked to reflect the latest changes in NLU 3.0.0+
- 200+SOTA Medical NLP Models NER, Resolution, Relations – John Snow Labs NLU3.0.0
-
200+ State of the Art Medical Models for NER, Entity Resolution, Relation Extraction, Assertion, Spark 3 and Python 3.8 support - John Snow Labs NLU 3.0.0
Graph NLU tutorial
Entity Resolution overview notebook
Relation extraction notebook
Medical Named Entity Extraction (NER) notebook
NLU on Github
simpletransformers
-
Huggingface is a great idea poorly executed.
You might try this: https://github.com/ThilinaRajapakse/simpletransformers
-
Gpt 2 124m using transformers
https://github.com/ThilinaRajapakse/simpletransformers/blob/master/simpletransformers/language_generation/language_generation_model.py#L146
-
Neural Search Tutorial
Getting embeddings from BERT Encoder
-
Neural Search Step-by-Step
Tutorial includes: - What is the Neural Search? - Getting embeddings from BERT Encoder - Using vector search engine Qdrant - Creating an API server with FastAPI.
-
Document Classification
If you want to do text classification hugging face transformers is great. There's also a simple version for it: https://github.com/ThilinaRajapakse/simpletransformers
-
A Shortly like user interface for GPT 2?
Here is an example script to finetune a GPT-2 model: https://github.com/ThilinaRajapakse/simpletransformers/blob/master/examples/language_generation/fine_tune.py
What are some alternatives?
spark-nlp - State of the Art Natural Language Processing
BERTweet - BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)
spark-nlp-display - A library for the simple visualization of different types of Spark NLP annotations.
minGPT - A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
streamlit-webrtc-example - Real time video and audio processing examples with Streamlit and streamlit-webrtc
layout-parser - A Unified Toolkit for Deep Learning Based Document Image Analysis
frame-semantic-transformer - Frame Semantic Parser based on T5 and FrameNet
kiri - Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
fastapi - FastAPI framework, high performance, easy to learn, fast to code, ready for production
PromCSE - Code for "Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (EMNLP 2022)"
rasa - 💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants