Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
XueyingJia
/
pythia-1b-online-dpo-HH-merge-rewardmodel-duplicated
like
0
Transformers
Safetensors
XueyingJia/online_dpo_repo
Generated from Trainer
trl
online-dpo
Inference Endpoints
arxiv:
2402.04792
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
pythia-1b-online-dpo-HH-merge-rewardmodel-duplicated
1 contributor
History:
7 commits
XueyingJia
End of training
0493e40
verified
17 days ago
.gitattributes
Safe
1.52 kB
initial commit
17 days ago
README.md
Safe
2.55 kB
End of training
17 days ago
adapter_config.json
Safe
655 Bytes
Model save
17 days ago
adapter_model.safetensors
Safe
4.2 MB
LFS
Model save
17 days ago
special_tokens_map.json
Safe
587 Bytes
Model save
17 days ago
tokenizer.json
Safe
3.56 MB
Model save
17 days ago
tokenizer_config.json
Safe
5.52 kB
Model save
17 days ago
training_args.bin
pickle
Detected Pickle imports (9)
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"trl.trainer.online_dpo_config.OnlineDPOConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"transformers.trainer_utils.HubStrategy"
How to fix it?
6.07 kB
LFS
Model save
17 days ago