Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
smohammadi
/
llama2-lora-aligned-cpo
like
0
PEFT
Safetensors
trl
cpo
Generated from Trainer
License:
gemma
Model card
Files
Files and versions
Community
Use this model
main
llama2-lora-aligned-cpo
1 contributor
History:
4 commits
This model has 1 file scanned as suspicious.
Show
files
smohammadi
Model save
b5323e5
verified
3 months ago
.gitattributes
Safe
1.57 kB
Training in progress, step 500
3 months ago
README.md
Safe
1.42 kB
Model save
3 months ago
adapter_config.json
Safe
639 Bytes
Training in progress, step 500
3 months ago
adapter_model.safetensors
Safe
3.7 MB
LFS
Training in progress, step 1000
3 months ago
special_tokens_map.json
Safe
636 Bytes
Training in progress, step 500
3 months ago
tokenizer.json
Safe
17.5 MB
LFS
Training in progress, step 500
3 months ago
tokenizer.model
Safe
4.24 MB
LFS
Training in progress, step 500
3 months ago
tokenizer_config.json
Safe
40.3 kB
Training in progress, step 500
3 months ago
training_args.bin
Suspicious
pickle
Detected Pickle imports (9)
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"trl.trainer.cpo_config.CPOConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.state.PartialState"
,
"torch.device"
How to fix it?
5.56 kB
LFS
Training in progress, step 500
3 months ago