Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Qwen
/
Qwen-1_8B-Chat-Int8
like
4
Follow
Qwen
1,861
Text Generation
Transformers
Safetensors
Chinese
English
qwen
custom_code
8-bit precision
gptq
arxiv:
2309.16609
arxiv:
2305.08322
arxiv:
2009.03300
Model card
Files
Files and versions
Community
2
Train
Use this model
ae343e1
Qwen-1_8B-Chat-Int8
/
quantize_config.json
xingzhang
update
7442c3d
12 months ago
raw
Copy download link
history
blame
Safe
214 Bytes
{
"bits"
:
8
,
"group_size"
:
128
,
"damp_percent"
:
0.01
,
"desc_act"
:
false
,
"static_groups"
:
false
,
"sym"
:
true
,
"true_sequential"
:
true
,
"model_name_or_path"
:
null
,
"model_file_base_name"
:
"model"
}