LLaMA-7B (protein-oriented instruction-tuned)

Training compute

2.8×10²² FLOP

Parameters

7B

Published

Oct 2, 2023

LLaMA-7B (protein-oriented instruction-tuned) is an AI model developed by Zhejiang University (ZJU) (China), first published in October 2023. It works in the language and biology domain, on tasks such as protein folding prediction, protein generation, other biological modeling and 2 more.

Training it took an estimated 2.8×10²² FLOP of compute (estimation method: hardware,operation counting). The model has 7,000,000,000 parameters. It was trained on roughly 5.1B datapoints.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of LLaMA-7B. The reference paper has 145 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Zhejiang University (ZJU)
Country of organization: China
Domain: Language, Biology
Task: Protein folding prediction, Protein generation, Other Biological Modeling, Protein or nucleotide language model (pLM/nLM), Protein question answering
Training compute: 2.8×10²² FLOP
Compute estimation method: Hardware, Operation counting
Parameters: 7,000,000,000
Dataset size: 5.1B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: LLaMA-7B
Citations: 145
Epoch confidence: Confident