Hugging Face's logo

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

Model card Files Community
Llama-2-70b-chat-hf-trt-fp8

Commit History

update models for newer trt 0.6.1 version
dd20dba

yessenzhar commited on

add weights compiled by 0.6.1 trtllm
2d64b65

yessenzhar commited on

Revert
03200fe

Pernekhan commited on

Try fixing exclude_input_in_output value field
6005d8a

Pernekhan commited on

exclude input in ouput
891ad10

yessenzhar commited on

try bugfix
151b0f6

yessenzhar commited on

remove hardcoded weights and tokenizer dirs, replace with template
5de4d5c

yessenzhar commited on

remove print
d5c7a29

yessenzhar commited on

add trtllm weights
0e96839

yessenzhar commited on

add model cache
2354c48

yessenzhar commited on

add smaller files
a83b588

yessenzhar commited on

initial commit
210dc9f

Pernekhan commited on