Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Holarissun
/
RM-helpful_helpful_contrast_loraR64_20000_gemma2b_lr1e-05_bs2_g4
like
0
PEFT
Safetensors
trl
reward-trainer
Generated from Trainer
License:
gemma
Model card
Files
Files and versions
xet
Community
Use this model
main
RM-helpful_helpful_contrast_loraR64_20000_gemma2b_lr1e-05_bs2_g4
51.3 MB
1 contributor
History:
2 commits
Holarissun
End of training
6331fe1
verified
over 1 year ago
.gitattributes
1.57 kB
End of training
over 1 year ago
README.md
1.61 kB
End of training
over 1 year ago
adapter_config.json
612 Bytes
End of training
over 1 year ago
adapter_model.safetensors
29.5 MB
xet
End of training
over 1 year ago
special_tokens_map.json
636 Bytes
End of training
over 1 year ago
tokenizer.json
17.5 MB
xet
End of training
over 1 year ago
tokenizer.model
4.24 MB
xet
End of training
over 1 year ago
tokenizer_config.json
40 kB
End of training
over 1 year ago
training_args.bin
4.98 kB
xet
End of training
over 1 year ago
