Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DrishtiSharma
/
dolphin-mistral-dpo-ultrafeedback-binarized-preferences-kto_pair
like
0
PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
d9f60e6
dolphin-mistral-dpo-ultrafeedback-binarized-preferences-kto_pair
File size: 51 Bytes
d9f60e6
1
2
3
4
5
{
"<|im_end|>"
:
32000
,
"<|im_start|>"
:
32001
}