Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
RichardErkhov
/
Qwen_-_Qwen2.5-7B-Instruct-4bits
like
0
Safetensors
qwen2
4-bit precision
bitsandbytes
arxiv:
2309.00071
arxiv:
2407.10671
Model card
Files
Files and versions
Community
1889ab9
Qwen_-_Qwen2.5-7B-Instruct-4bits
/
generation_config.json
Commit History
uploaded model
3b02864
verified
RichardErkhov
commited on
Oct 18