Sapling Logo

MPT-7B vs. OPT

LLM Comparison

MPT-7B

Overview

MPT-7B is a set of models that are part of MosaicML's Foundation Series. Trained on 1T tokens, the developers state that it matches the performance of LLaMA while also being open source. In addition to the base model, the developers also offer MPT-7B-Instruct, MPT-7B-Chat, and MPT-7B-StoryWriter-65k+, the last of which is trained on a context length of 65K tokens.

Initial release: 2023-05-05

Reference

https://www.mosaicml.com/blog/mpt-7b

Further Reading

OPT

Overview

Open Pre-trained Transformer Language Models (OPT) is part of the family of open source models designed to replicate GPT-3, with similar decoder-only architecture. It has since been superseded by models such as LLaMA, GPT-J, and Pythia.

Initial release: 2022-05-03

Reference

https://github.com/facebookresearch/metaseq/tree/main/projects/OPT

Further Reading

Looking for an LLM API/SDK that works out of the box?

Sapling API
More Comparisons

MPT-7B

OPT
Products & Features
Instruct Models
Coding Capability
Customization
Finetuning
Open Source
License Apache 2.0 NA
Model Sizes 7B 1.3B, 2.7B, 6.7B, 13B, 30B, 66B, 175B

Other MPT-7B Comparisons

MPT-7B vs. Alpaca MPT-7B vs. BLOOM MPT-7B vs. Cerebras-GPT MPT-7B vs. Dolly MPT-7B vs. FLAN-T5 MPT-7B vs. FLAN-UL2 MPT-7B vs. GPT-J MPT-7B vs. GPT4All MPT-7B vs. GPTNeo MPT-7B vs. Koala MPT-7B vs. LLaMA MPT-7B vs. OpenAssistant MPT-7B vs. OpenLLaMA MPT-7B vs. OPT MPT-7B vs. Pythia MPT-7B vs. RedPajama-INCITE MPT-7B vs. StableLM MPT-7B vs. StableVicuna MPT-7B vs. Vicuna

Other OPT Comparisons

OPT vs. Alpaca OPT vs. BLOOM OPT vs. Cerebras-GPT OPT vs. Dolly OPT vs. FLAN-T5 OPT vs. FLAN-UL2 OPT vs. GPT-J OPT vs. GPT4All OPT vs. GPTNeo OPT vs. Koala OPT vs. LLaMA OPT vs. MPT-7B OPT vs. OpenAssistant OPT vs. OpenLLaMA OPT vs. Pythia OPT vs. RedPajama-INCITE OPT vs. StableLM OPT vs. StableVicuna OPT vs. Vicuna

Undecided?

Get Advice