Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
phi-2-gpo-newSFT-b0.001-v6-lightai-i1
like
0
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
License:
apache-2.0
Model card
Files
Files and versions
Community
Use this model
main
phi-2-gpo-newSFT-b0.001-v6-lightai-i1
1 contributor
History:
3 commits
BraylonDash
End of training
2cd2488
verified
3 months ago
.gitattributes
1.52 kB
initial commit
3 months ago
README.md
1.44 kB
End of training
3 months ago
adapter_config.json
607 Bytes
Model save
3 months ago
adapter_model.safetensors
168 MB
LFS
Model save
3 months ago
added_tokens.json
1.08 kB
Model save
3 months ago
all_results.json
193 Bytes
Model save
3 months ago
config.json
928 Bytes
End of training
3 months ago
merges.txt
456 kB
Model save
3 months ago
special_tokens_map.json
587 Bytes
Model save
3 months ago
tokenizer.json
2.11 MB
Model save
3 months ago
tokenizer_config.json
7.82 kB
Model save
3 months ago
train_results.json
193 Bytes
Model save
3 months ago
trainer_state.json
8.26 kB
Model save
3 months ago
training_args.bin
5.88 kB
LFS
Model save
3 months ago
vocab.json
798 kB
Model save
3 months ago