Remove unused pytorch_model.bin.index.json

Add 8bit quantized model

remove useless pt

Add Updated v1.1b

Create README.md

Update Model with <|sep|> aware(newline performance upgrade)

Finetune model with following https://github.com/tatsu-lab/stanford_alpaca#fine-tuning

Add 2e5_1epoch/checkpoint-5067 model

initial commit