Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DeepInfra
/
Llama-2-70b-chat-hf-trt-fp8
like
0
Follow
Deep Infra Inc.
4
License:
llama2
Model card
Files
Files and versions
Community
891ad10
Llama-2-70b-chat-hf-trt-fp8
2 contributors
History:
8 commits
yessenzhar
exclude input in ouput
891ad10
11 months ago
ensemble
add smaller files
11 months ago
postprocessing
try bugfix
11 months ago
preprocessing
remove hardcoded weights and tokenizer dirs, replace with template
11 months ago
tensorrt_llm
exclude input in ouput
11 months ago
.gitattributes
Safe
1.91 kB
add trtllm weights
11 months ago
.gitignore
Safe
6 Bytes
add smaller files
11 months ago
README.md
Safe
24 Bytes
initial commit
11 months ago