Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
hiroki-rad
/
gemma2-2b-dpo
like
0
Transformers
Safetensors
hiroki-rad/elyza_tasks-dpo-1500
Japanese
Generated from Trainer
trl
dpo
arxiv:
2305.18290
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
gemma2-2b-dpo
3.73 GB
1 contributor
History:
3 commits
hiroki-rad
Update README.md
d56386b
verified
about 1 year ago
DPO
hiroki-rad/gemma2-2b-dpo
about 1 year ago
reference
hiroki-rad/gemma2-2b-dpo
about 1 year ago
.gitattributes
1.57 kB
hiroki-rad/gemma2-2b-dpo
about 1 year ago
README.md
2.67 kB
Update README.md
about 1 year ago
special_tokens_map.json
636 Bytes
hiroki-rad/gemma2-2b-dpo
about 1 year ago
tokenizer.json
34.4 MB
xet
hiroki-rad/gemma2-2b-dpo
about 1 year ago
tokenizer.model
4.24 MB
xet
hiroki-rad/gemma2-2b-dpo
about 1 year ago
tokenizer_config.json
46.6 kB
hiroki-rad/gemma2-2b-dpo
about 1 year ago
training_args.bin
6.07 kB
xet
hiroki-rad/gemma2-2b-dpo
about 1 year ago