Articles in NLP

2 articles

Crafting Text Generators: A Dive into Transformer Architecture

Crafting Text Generators: A Dive into Transformer Architecture

  • AI Geek Programmer
  • NLP
  • 19 August 2023

A small decoder-based language model. Or how to use part of the Transformer architecture to generate text resembling a well-known literary work (Pytorch).

Read article
Fine-tuning with limited hardware resources

Fine-tuning with limited hardware resources

  • AI Geek Programmer
  • NLP
  • 26 June 2023

Efficient fine-tuning of a large language model in Google Colab using PEFT, LoRa and quantization (base model: RedPajama INCITE Chat 3B)

Read article