Hugging Face
Models
Datasets
Spaces
Posts
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
Inference Endpoints
arxiv:
2305.18290
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
gemma2-2b-dpo
1 contributor
History:
3 commits
hiroki-rad
Update README.md
d56386b
verified
5 days ago
DPO
hiroki-rad/gemma2-2b-dpo
5 days ago
reference
hiroki-rad/gemma2-2b-dpo
5 days ago
.gitattributes
Safe
1.57 kB
hiroki-rad/gemma2-2b-dpo
5 days ago
README.md
Safe
2.67 kB
Update README.md
5 days ago
special_tokens_map.json
Safe
636 Bytes
hiroki-rad/gemma2-2b-dpo
5 days ago
tokenizer.json
Safe
34.4 MB
LFS
hiroki-rad/gemma2-2b-dpo
5 days ago
tokenizer.model
Safe
4.24 MB
LFS
hiroki-rad/gemma2-2b-dpo
5 days ago
tokenizer_config.json
Safe
46.6 kB
hiroki-rad/gemma2-2b-dpo
5 days ago
training_args.bin
pickle
Detected Pickle imports (10)
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"trl.trainer.dpo_config.FDivergenceType"
,
"transformers.trainer_utils.HubStrategy"
,
"trl.trainer.dpo_config.DPOConfig"
How to fix it?
6.07 kB
LFS
hiroki-rad/gemma2-2b-dpo
5 days ago