Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
avans06
/
Meta-Llama-3.1-8B-Instruct-ct2-int8_float16
like
0
Text Generation
PyTorch
8 languages
facebook
meta
llama
llama-3
ctranslate2
quantization
int8
float16
conversational
arxiv:
2204.05149
License:
llama3.1
Model card
Files
Files and versions
Community
6e4cc9d
Meta-Llama-3.1-8B-Instruct-ct2-int8_float16
/
generation_config.json
avans06
Upload 11 files
6e4cc9d
verified
about 1 month ago
raw
Copy download link
history
blame
Safe
184 Bytes
{
"bos_token_id"
:
128000
,
"do_sample"
:
true
,
"eos_token_id"
:
[
128001
,
128008
,
128009
]
,
"temperature"
:
0.6
,
"top_p"
:
0.9
,
"transformers_version"
:
"4.42.3"
}