Make sure hidden state and wte weights are on same device when in parallel model.

Update modeling_mpt.py

Update modeling_mpt.py

Update modeling_mpt.py

Update modeling_mpt.py

Upload pytorch_model-00001-of-00002.bin

Update modeling_mpt.py

Upload pytorch_model-00002-of-00002.bin

Rename tokenizer_config (2).json to tokenizer_config.json

Rename tokenizer (1).json to tokenizer.json

Rename config (1).json to config.json

Rename pytorch_model.bin.index (2).json to pytorch_model.bin.index.json

Upload 16 files

Delete README.md

initial commit