casperhansen
/

mpt-7b-8k-chat-awq

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

mpt-7b-8k-chat-awq

1 contributor

History: 10 commits

casperhansen's picture

Set initial device to cuda:0 for faster initial loading

364bcfc about 1 year ago