Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Liu-Xiang
/
doplhin-dpo
like
0
PEFT
TensorBoard
Safetensors
mistral
trl
dpo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
b2a5f12
doplhin-dpo
/
added_tokens.json
Liu-Xiang
End of training
b56ef43
verified
11 months ago
raw
Copy download link
history
blame
Safe
51 Bytes
{
"<|im_end|>"
:
32000
,
"<|im_start|>"
:
32001
}