What's in the RedPajama-Data-1T LLM training set

RedPajama is “a project to create leading open-source models, starts by reproducing LLaMA training dataset of over 1.2 trillion tokens”. It’s a collaboration between Together, Ontocord.ai, ETH DS3Lab, Stanford CRFM, …

Red Pajama: An Open-Source Llama Model

Catching up on the weird world of LLMs

The Latest Open Source LLMs and Datasets

Catching up on the weird world of LLMs

65-Billion-Parameter Large Model Pretraining Accelerated by 38

Fine-Tuning Insights: Lessons from Experimenting with RedPajama

LLaMA clone: RedPajama – first open-source decentralized AI with

Fine-Tuning Insights: Lessons from Experimenting with RedPajama

Local Large Language Models

Ahead of AI #8: The Latest Open Source LLMs and Datasets