Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DeepInfra
/
Llama-2-70b-chat-hf-trt-fp8
like
0
Follow
Deep Infra Inc.
5
License:
llama2
Model card
Files
Files and versions
Community
2d64b65
Llama-2-70b-chat-hf-trt-fp8
2 contributors
History:
11 commits
yessenzhar
add weights compiled by 0.6.1 trtllm
2d64b65
about 1 year ago
ensemble
add smaller files
about 1 year ago
postprocessing
try bugfix
about 1 year ago
preprocessing
remove hardcoded weights and tokenizer dirs, replace with template
about 1 year ago
tensorrt_llm
add weights compiled by 0.6.1 trtllm
about 1 year ago
.gitattributes
Safe
1.91 kB
add trtllm weights
about 1 year ago
.gitignore
Safe
6 Bytes
add smaller files
about 1 year ago
README.md
Safe
24 Bytes
initial commit
about 1 year ago