Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
Tulu-13B-SuperHOT-8K-GPTQ
like
1
Text Generation
Transformers
Safetensors
llama
custom_code
text-generation-inference
4-bit precision
gptq
arxiv:
2306.04751
arxiv:
2302.13971
arxiv:
2304.07327
License:
other
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
4ee67f4
Tulu-13B-SuperHOT-8K-GPTQ
/
quantize_config.json
TheBloke
Update for Transformers GPTQ support
4ee67f4
about 1 year ago
raw
Copy download link
history
blame
No virus
158 Bytes
{
"bits"
:
4
,
"group_size"
:
128
,
"damp_percent"
:
0.01
,
"desc_act"
:
false
,
"sym"
:
true
,
"true_sequential"
:
true
,
"model_file_base_name"
:
"model"
}