metadata
datasets:
- ehartford/dolphin
license: apache-2.0
Base Model : mosaicml/mpt-30b
Tool : MosaicML's llm-foundry (https://github.com/mosaicml/llm-foundry)
Dataset : Entire flan1m-GPT4 dataset
Config yaml with Model Params : https://huggingface.co/iamplus/mpt-30b-v4/blob/main/mpt-30b_v4.yaml
Description : mosaicml/mpt-30b -> Finetuning on (Entire flan3m-GPT3.5 dataset for 4 epochs)
Prompt Format :
<system>: [system prompt]
<human>: [question]
<bot>: