Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
dctanner
/
sablo-pebble-mistral-dpo-lora-oasst2_dpo_pairs_en
like
0
PEFT
TensorBoard
Safetensors
sablo/oasst2_dpo_pairs_en
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
main
sablo-pebble-mistral-dpo-lora-oasst2_dpo_pairs_en
File size: 51 Bytes
82029ca
1
2
3
4
5
{
"<|im_end|>"
:
32000
,
"<|im_start|>"
:
32001
}