Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
prosecalign
/
phi3m0128-wds-0.1-kendall-onof-ofif-corr-max-2-simpo-max1500-default
like
0
Follow
Proactive Security Alignment
5
Transformers
Safetensors
Generated from Trainer
llama-factory
Inference Endpoints
arxiv:
2305.18290
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
1e7983b
phi3m0128-wds-0.1-kendall-onof-ofif-corr-max-2-simpo-max1500-default
1 contributor
History:
2 commits
ziansu
Training in progress, step 50
1e7983b
verified
27 days ago
.gitattributes
Safe
1.52 kB
initial commit
27 days ago
adapter_config.json
Safe
766 Bytes
Training in progress, step 50
27 days ago
adapter_model.safetensors
Safe
25.2 MB
LFS
Training in progress, step 50
27 days ago
special_tokens_map.json
Safe
563 Bytes
Training in progress, step 50
27 days ago
tokenizer.json
Safe
3.62 MB
Training in progress, step 50
27 days ago
tokenizer_config.json
Safe
3.5 kB
Training in progress, step 50
27 days ago
trainer_log.jsonl
Safe
1.62 kB
Training in progress, step 50
27 days ago
training_args.bin
pickle
Detected Pickle imports (14)
"transformers.training_args_seq2seq.Seq2SeqTrainingArguments"
,
"accelerate.utils.dataclasses.DistributedType"
,
"torch.device"
,
"transformers.trainer_utils.SaveStrategy"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"accelerate.state.PartialState"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"torch.float16"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
How to fix it?
7.22 kB
LFS
Training in progress, step 50
27 days ago
