Open-Assistant SST SFT-1 Pythia-12B or oasst-sft-1-pythia-12b is a GPT-style large language model that has been trained to follow human instructions. Based on EleutherAI’s pythia-12b model, oasst-sft-1-pythia-12b was trained by Open-Assistant on ~22k human demonstrations of assistant conversations. This data was collected through the https://open-assistant.io/ human feedback web app before March 7, 2023.

Model description

oasst-sft-1-pythia-12b is a fine-tuned version of EleutherAI’s pythia-12b, a GPT-style causal language model trained on the Pile. See here for more information about the model architecture. oasst-sft-1-pythia-12b was developed by fine-tuning the pythia-12b checkpoint on roughly 22,000 instruction examples that were generated by the Open-Assistant community.

Intended use

This is an experimental model that has been trained to act as an assistant, such that it responds to user queries with helpful answers. However, it has not been stress-tested and there are no guaranteed protections from malfunctions, inaccuracies, or harmful responses.

Ethical considerations

This model is not designed to avoid harmful or undesirable behavior and its output should not be unconditionally trusted in contexts where there are risks or costs of inaccuracy.