Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
XueyingJia
/
pythia-1b-deduped-hh-online-dpo
like
0
Text Generation
Transformers
Safetensors
XueyingJia/online_dpo_repo
gpt_neox
Generated from Trainer
trl
online-dpo
conversational
text-generation-inference
Inference Endpoints
arxiv:
2402.04792
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
9f68452
pythia-1b-deduped-hh-online-dpo
1 contributor
History:
2 commits
XueyingJia
Training in progress, step 1508
9f68452
verified
3 months ago
.gitattributes
1.52 kB
initial commit
3 months ago
adapter_config.json
655 Bytes
Training in progress, step 1508
3 months ago
adapter_model.safetensors
8.39 MB
LFS
Training in progress, step 1508
3 months ago
special_tokens_map.json
579 Bytes
Training in progress, step 1508
3 months ago
tokenizer.json
3.56 MB
Training in progress, step 1508
3 months ago
tokenizer_config.json
5.33 kB
Training in progress, step 1508
3 months ago
training_args.bin
pickle
Detected Pickle imports (9)
"torch.device"
,
"transformers.trainer_utils.IntervalStrategy"
,
"trl.trainer.online_dpo_config.OnlineDPOConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.SchedulerType"
How to fix it?
5.56 kB
LFS
Training in progress, step 1508
3 months ago