Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Qwen
/
Qwen-7B-Chat-Int8
like
8
Follow
Qwen
7.64k
Text Generation
Transformers
Safetensors
Chinese
English
qwen
custom_code
8-bit precision
gptq
arxiv:
5 papers
Model card
Files
Files and versions
Community
1
Train
Use this model
ce1512e
Qwen-7B-Chat-Int8
/
tokenizer_config.json
yangapku
upload model
ce1512e
about 1 year ago
raw
Copy download link
history
blame
Safe
173 Bytes
{
"model_max_length"
:
8192
,
"tokenizer_class"
:
"QWenTokenizer"
,
"auto_map"
:
{
"AutoTokenizer"
:
[
"tokenization_qwen.QWenTokenizer"
,
null
]
}
}