Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
martimfasantos
/
gemma-2-2b-it-mt-dpo-full_sardine
like
0
TensorBoard
Safetensors
sardinelab/MT-pref
gemma2
alignment-handbook
trl
dpo
Generated from Trainer
License:
gemma
Model card
Files
Files and versions
Metrics
Training metrics
Community
23c88d5
gemma-2-2b-it-mt-dpo-full_sardine
/
tokenizer.model
Commit History
Training in progress, step 100
1d6e648
verified
martimfasantos
commited on
Aug 8