Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
snoels
/
FinGEITje-7B-dpo
like
2
Text Generation
PEFT
TensorBoard
Safetensors
BramVanroy/ultra_feedback_dutch
Dutch
mistral
alignment-handbook
trl
dpo
Generated from Trainer
geitje
fingeitje
dutch
finance
conversational
4-bit precision
bitsandbytes
arxiv:
2410.12835
License:
cc-by-nc-4.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
main
FinGEITje-7B-dpo
/
all_results.json
Commit History
End of training
6028bf1
verified
snoels
commited on
Jul 22
Model save
b8ed563
verified
snoels
commited on
Jul 22