# ExLlamaV2 Measurements

Measurement files used to quantize models uploaded here.  Depending on the model type one of the following datasets is used for calibration:
* General chat or instruct model: ThePile [0007.parquet](https://huggingface.co/datasets/EleutherAI/the_pile_deduplicated/resolve/refs%2Fconvert%2Fparquet/default/train/0007.parquet)
* Coding model: [WizardLM_evol_instruct_V2_196k](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k)
* RP model: [pippa.parquet](https://discord.com/channels/1111983596572520458/1152699950208139415/1152700764230271076) (from Undi of TheBloke Discord)
* Japanese model: filtered text from file [Japanese Wiki file jawikibooks-20231023-cirrussearch](https://dumps.wikimedia.org/other/cirrussearch/20231023/jawikibooks-20231023-cirrussearch-content.json.gz)