Rename awq_model_w4_g128.pt to pytorch_model.bin

Update config.json

Update quant_config.json

Rename mpt-7b-8k-chat-awq-w4-g128.pt to awq_model_w4_g128.pt

Create quant_config.json

Update README.md

Update README.md

Set initial device to cuda:0 for faster initial loading

Delete .gitattributes copy

Delete README copy.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README

MPT 7B 8K quantized

initial commit