Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
kuleshov
/
opt-6.7b-4bit
like
0
Text Generation
Transformers
opt
Inference Endpoints
text-generation-inference
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
894a772
opt-6.7b-4bit
/
quant_config.json
kuleshov
first commit
894a772
10 months ago
raw
history
blame
No virus
182 Bytes
{
"dataset"
:
"c4"
,
"bits"
:
4
,
"nsamples"
:
128
,
"groupsize"
:
64
,
"act_order"
:
true
,
"percdamp"
:
0.01
,
"seed"
:
0
,
"nearest"
:
false
,
"save"
:
"./bloom-560m-quantized"
}