Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
quyanh
/
pythia-2.8b-dpo
like
0
Transformers
Safetensors
Generated from Trainer
dpo
trl
arxiv:
2305.18290
Model card
Files
Files and versions
xet
Community
Train
Deploy
Use this model
main
pythia-2.8b-dpo
175 MB
1 contributor
History:
105 commits
This model has 1 file scanned as suspicious.
Show
files
quyanh
Model save
a651235
verified
3 months ago
final_model
Model save
3 months ago
.gitattributes
Safe
1.52 kB
initial commit
3 months ago
README.md
Safe
2.52 kB
Training in progress, step 100
3 months ago
adapter_config.json
Safe
941 Bytes
DPO LoRA checkpoint - step 100 (eval_loss: 0.6984)
3 months ago
adapter_model.safetensors
83.9 MB
xet
Training in progress, step 10050
3 months ago
special_tokens_map.json
Safe
587 Bytes
Tokenizer - DPO LoRA checkpoint - step 100 (eval_loss: 0.6984)
3 months ago
tokenizer.json
Safe
3.56 MB
Tokenizer - DPO LoRA checkpoint - step 100 (eval_loss: 0.6984)
3 months ago
tokenizer_config.json
Safe
5.07 kB
Tokenizer - DPO LoRA checkpoint - step 100 (eval_loss: 0.6984)
3 months ago
training_args.bin
Unsafe
pickle
Detected Pickle imports (11)
"__main__.DPOTrainingArguments"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"trl.trainer.dpo_config.FDivergenceType"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.SaveStrategy"
,
"transformers.training_args.OptimizerNames"
,
"torch.device"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"accelerate.utils.dataclasses.DistributedType"
How to fix it?
6.8 kB
xet
Training in progress, step 100
3 months ago