Commit History

add raw llama-7B model
9c75415

RonanMcGovern commited on

turning inference off as the model is too large (>10 GB)
dce14eb

RonanMcGovern commited on

try turning on hosted inference
f6e2b95

RonanMcGovern commited on

add improved inference options
9f9b784

RonanMcGovern commited on

make 7B model license Llama 2.
6a55a1a

RonanMcGovern commited on

move up inference guide
7de10d4

RonanMcGovern commited on

remove space between <s> and [INST]
17fe3c5

RonanMcGovern commited on

update license now that model has been updated
2883f51

RonanMcGovern commited on

add instructions on function calling
ff4b3f0

RonanMcGovern commited on