Commit History

Adding `safetensors` variant of this model
f65201e
verified

SFconvertbot commited on

Rename awq_model_w4_g128.pt to pytorch_model.bin
7574465

casperhansen commited on

Update config.json
56e7db5

casperhansen commited on

Update quant_config.json
6c68c97

casperhansen commited on

Rename mpt-7b-8k-chat-awq-w4-g128.pt to awq_model_w4_g128.pt
8890e78

casperhansen commited on

Create quant_config.json
f176efe

casperhansen commited on

Set initial device to cuda:0 for faster initial loading
364bcfc

casperhansen commited on

Delete .gitattributes copy
98f6fc3

casperhansen commited on

Delete README copy.md
8ef5699

casperhansen commited on

MPT 7B 8K quantized
5c660fe

casperhansen commited on