A little less than a year ago, I joined the awesome Cohere team. The company trains massive language models (both GPT-like and BERT-like) and offers them as an API (which also supports finetuning). Its founders include Google Brain alums including co-authors of the original Transformers paper. It’s a fascinating role where I get to help companies and developers put these massive models to work solving real-world problems.
I love that I get to share some of the intuitions developers need to start problem-solving with these models. Even though I’ve been working very closely on pretrained Transformers for the past several years (for this blog and in developing Ecco), I’m enjoying the convenience of problem-solving with managed language models as it frees up the restrictions of model loading/deployment and memory/GPU management.
These are some of the articles I wrote and collaborated on with colleagues over the last few months:
This is a high-level intro to large language models to people who are new to them. It establishes the difference between generative (GPT-like) and representation (BERT-like) models and examples use cases for them.
This is one of the first articles I got to write. It’s extracted from a much larger document that I wrote to explore some of the visual language to use in explaining the application of these models.
Massive GPT models open the door for a new way of programming. If you structure the input text in the right way, you can useful (and often fascinating) results for a lot of taasks (e.g. text classification, copy writing, summarization…etc).
This article visually demonstrates four principals to create prompts effectively.
This is a walkthrough of creating a simple summarization system. It links to a jupyter notebook which includes the code to start experimenting with text generation and summarization.
The end of this notebook shows an important idea I want to spend more time on in the future. That of how to rank/filter/select the best from amongst multiple generations.
Semantic search has to be one of the most exciting applications of sentence embedding models. This tutorials implements a “similar questions” functionality using sentence embeddings and a a vector search library.
This one is a little bit more technical. It explains the parameters you tweak to adjust a GPT’s decoding strategy — the method with which the system picks output tokens.