From 6e5eb22d7032ecc15a733fcc0fc25da2b7a32d43 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Shivanand=20Roy=20=F0=9F=91=8B?= Date: Sun, 20 Jun 2021 21:25:06 +0000 Subject: [PATCH] Update README.md --- README.md | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 85e3d61..137e13f 100644 --- a/README.md +++ b/README.md @@ -23,17 +23,20 @@ license: mit --- # T5 One Line Summary -A T5 model trained on 370,000 research papers, to generate one line summary based on description/abstract of the papers - -Trained with [**simpleT5**](https://https://github.com/Shivanandroy/simpleT5)⚡️in just 3 lines of code -- [**simpleT5**](https://https://github.com/Shivanandroy/simpleT5)⚡️ is a python package built on top of **pytorch lightning** and **transformers**🤗, to quickly train T5 models. +A T5 model trained on 370,000 research papers, to generate one line summary based on description/abstract of the papers using [**simpleT5**](https://https://github.com/Shivanandroy/simpleT5) (built on top of pytorch lightning⚡️ & transformers🤗 to train T5 models) ## Usage:[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1HrfT8IKLXvZzPFpl1EhZ3s_iiXG3O2VY?usp=sharing) ```python -abstract = """We describe a system called Overton, whose main design goal is to support engineers in building, monitoring, and improving production machine learning systems. Key challenges engineers face are monitoring fine-grained quality, diagnosing errors in sophisticated applications, and handling contradictory or incomplete supervision data. Overton automates the life cycle of model construction, deployment, and monitoring by providing a set of novel high-level, declarative abstractions. Overton's vision is to shift developers to these higher-level tasks instead of lower-level machine learning tasks. In fact, using Overton, engineers can build deep-learning-based applications without writing any code in frameworks like TensorFlow. For over a year, Overton has been used in production to support multiple applications in both near-real-time applications and back-of-house processing. In that time, Overton-based applications have answered billions of queries in multiple languages and processed trillions of records reducing errors 1.7-2.9 times versus production systems. +abstract = """We describe a system called Overton, whose main design goal is to support engineers in building, monitoring, and improving production +machine learning systems. Key challenges engineers face are monitoring fine-grained quality, diagnosing errors in sophisticated applications, and +handling contradictory or incomplete supervision data. Overton automates the life cycle of model construction, deployment, and monitoring by providing a +set of novel high-level, declarative abstractions. Overton's vision is to shift developers to these higher-level tasks instead of lower-level machine learning tasks. +In fact, using Overton, engineers can build deep-learning-based applications without writing any code in frameworks like TensorFlow. For over a year, +Overton has been used in production to support multiple applications in both near-real-time applications and back-of-house processing. In that time, +Overton-based applications have answered billions of queries in multiple languages and processed trillions of records reducing errors 1.7-2.9 times versus production systems. """ ``` -Transformers🤗 +### Using Transformers🤗 ```python model_name = "snrspeaks/t5-one-line-summary" @@ -50,7 +53,7 @@ print(preds) "Overton: A System for Building, Monitoring, and Improving Production Machine Learning Systems", "Overton: Building, Monitoring, and Improving Production Machine Learning Systems"] ``` -simpleT5⚡️ +### Using simpleT5⚡️ ```python # pip install --upgrade simplet5 from simplet5 import SimpleT5