Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
robinsmits
/
Qwen1.5-7B-Dutch-Chat-Dpo
like
0
Text Generation
PEFT
TensorBoard
Safetensors
BramVanroy/ultra_feedback_dutch_cleaned
Dutch
trl
dpo
conversational
Generated from Trainer
qwen2
arxiv:
2309.16609
License:
cc-by-nc-4.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
1
Use this model
main
Qwen1.5-7B-Dutch-Chat-Dpo
/
reference
1 contributor
History:
1 commit
robinsmits
End of training
b7e48de
verified
8 months ago
adapter_config.json
Safe
694 Bytes
End of training
8 months ago
adapter_model.safetensors
Safe
640 MB
LFS
End of training
8 months ago