Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
TheBloke
/
Falcon-7B-Instruct-GPTQ
like
64
Text Generation
Transformers
Safetensors
tiiuae/falcon-refinedweb
English
RefinedWebModel
custom_code
text-generation-inference
4-bit precision
gptq
arxiv:
4 papers
License:
apache-2.0
Model card
Files
Files and versions
Community
19
Train
Deploy
Use this model
d6ce55f
Falcon-7B-Instruct-GPTQ
/
quantize_config.json
TheBloke
Update for Transformers GPTQ support
d6ce55f
about 1 year ago
raw
Copy download link
history
blame
Safe
157 Bytes
{
"bits"
:
4
,
"group_size"
:
64
,
"damp_percent"
:
0.01
,
"desc_act"
:
false
,
"sym"
:
true
,
"true_sequential"
:
true
,
"model_file_base_name"
:
"model"
}