Backup Structure
NLP University has two main parts, and six modules.
- The first part, consisting of Module 1 and Module 2, is guided towards theory.
- The second part, consisting of the last four modules is guided towards practice and know-how, including thorough tutorials on how to use and deploy the Cohere models.
Let me tell you about these one by one.
Part 1: Theory
Section titled “Part 1: Theory”Module 1: Introduction to NLP
Section titled “Module 1: Introduction to NLP”This course starts with Module 1, which contains an introduction to natural language processing, including history, language pre-processing techniques, and the machine learning models that have been used since NLP started, including supervised and unsupervised techniques. It ends with classification, including training classification models, evaluating them, and exploring their applications.
Module 2: What are Large Language Models?
Section titled “Module 2: What are Large Language Models?”Then comes Module 2, which talks about large language models. This course is geared towards understanding the architecture of transformers models, including embeddings, similarity, and attention, and their applications such as semantic search.
Part 2: Practice
Section titled “Part 2: Practice”Module 3: Text Representation with Cohere Endpoints
Section titled “Module 3: Text Representation with Cohere Endpoints”Module 3 is an introduction to Cohere’s endpoints, such as embed, classify, and summarize. In this module you’ll find several codelabs guided towards building cool applications such as clustering news, classifying text, or semantic search.
Module 4: Text Generation with Cohere Endpoints
Section titled “Module 4: Text Generation with Cohere Endpoints”Since generation is so important, and has been so relevant lately, module 4 is focused solely on generation. A very important part of generation is prompting, namely, being able to give the model the correct question or command in order to generate what you want. This is all done in the Cohere playground, so there’s no code involved. The second part then delves into the code, and teaches you how to use the generate endpoint and make build some cool applications such as summarization or entity extraction.
Module 5: Deployment
Section titled “Module 5: Deployment”Once you become an expert on how to build applications using the Cohere endpoints, the next step is to deploy them so other can use them! Module 3 teaches you how to deploy them in different platforms, such as Streamlit, AWS, and others, including Google sheets!
Bonus Material
Section titled “Bonus Material”If you want to get more practice into building bigger applications, we include a series of codelabs in which you can find a plethora of demos combining different endpoints to build some really cool applications, such as article recommenders, invoice extractors, lazy writers, name generators, question answering models, etc. Some of these have also been deployed as applications using different platforms.
We are so excited to have you learning with us. Happy learning!