Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
numen-tech
/
Llama-3-8B-Instruct-MopeyMule-w4a16g128asym
like
0
arxiv:
2308.13137
License:
llama3
Model card
Files
Files and versions
Community
main
Llama-3-8B-Instruct-MopeyMule-w4a16g128asym
/
README.md
numen-tech
Add weights
ffd9f4b
about 2 months ago
preview
code
|
raw
Copy download link
history
blame
contribute
delete
No virus
200 Bytes
metadata
license:
llama3
4-bit
OmniQuant
quantized version of
Llama-3-8B-Instruct-MopeyMule
.