DeepInfra
/

Llama-2-70b-chat-hf-trt-fp8

Model card Files Files and versions Community

Llama-2-70b-chat-hf-trt-fp8 / preprocessing

2 contributors

History: 2 commits

yessenzhar's picture

remove hardcoded weights and tokenizer dirs, replace with template

5de4d5c 11 months ago