Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
KYUNGYONG
/
EEVE-Korean-Instruct-7B-v2.0-Preview-mlx-4Bit
like
0
MLX
Safetensors
qwen2
Generated from Trainer
mlx-my-repo
4-bit precision
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
main
EEVE-Korean-Instruct-7B-v2.0-Preview-mlx-4Bit
File size: 46 Bytes
4aaabda
1
2
3
4
5
{
"</think>"
:
158322
,
"<think>"
:
158321
}