Llama 2 vs. Pythia

Overview

Llama 2 is Meta AI's open source LLM available both research and commercial use case.

The successor to LLaMA (henceforce "Llama 1"), Llama 2 was trained on 40% more data, has double the context length, and was tuned on a large dataset of human preferences (over 1 million such annotations) to ensure helpfulness and safety. It outperforms other open source models on both natural language understanding datasets as well as in head-to-head face-offs.

Initial release: 2023-07-18

Reference

https://ai.meta.com/llama/

Further Reading

• https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/

Overview

The most recent (as of May 2023) effort from EleutherAI, Pythia is a set of LLMs trained on The Pile. While it appears to outperform OPT and GPTNeo, its performance against GPT-J is unclear. Versions of Pythia have also been instruct-tuned by the team at Together.

Initial release: 2023-02-13

Reference

https://github.com/EleutherAI/pythia

Further Reading