Article originally posted here by Misha Obolonskyi. Reposted with permission. ChatGPT can carry on plausible conversations, write poetry in the style of Dylan Thomas or Shakespeare, and might do as good a job writing this blog post as I will! But without vector search, generative AI... Read more

This blog post presents how two open-source frameworks, Alpa and Ray, closely integrate to achieve the scale to train a 175B parameters OPT-175B model (equivalent to GPT-3) with pipeline parallelism up to 1024 A100 GPUs in collaboration with Nvidia. With this integration, our benchmarks show three scaling results: 1. Alpa... Read more

The latest wave of innovation around large language models (LLMs), such as ChatGPT and GPT-4, is rapidly transforming the world of bot building. Natural language processing (NLP) and machine learning have long formed the foundation for building intelligent bots, but the capabilities of these LLMs are... Read more

Large Language Models (LLMs) have revolutionized the field of natural language processing (NLP) and opened up a myriad of possibilities for various applications. With the recent rise in popularity of the LangChain framework, developers are now able to create powerful end-to-end user-facing applications by chaining different steps... Read more

Natural language processing (NLP) has been growing in awareness over the last few years, and with the popularity of ChatGPT and GPT-3 in 2022, NLP is now on the top of peoples’ minds when it comes to AI. Developing NLP tools isn’t so straightforward, and requires... Read more

The goal of this application is to demonstrate how the NLP task of text style transfer can be applied to enhance the human writing experience. In this sense, we intend to peel back the curtains on how an intelligent writing assistant might function — walking through the logical... Read more