Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
wwendelin
/
llama8b-dpo-jpgt
like
0
PEFT
Safetensors
trl
dpo
Generated from Trainer
License:
llama3
Model card
Files
Files and versions
Community
Use this model
main
llama8b-dpo-jpgt
1 contributor
History:
7 commits
wwendelin
Training in progress, step 17
db1a9fc
verified
7 days ago
.gitattributes
1.52 kB
initial commit
about 2 months ago
README.md
1.18 kB
Model save
7 days ago
adapter_config.json
740 Bytes
Training in progress, step 17
7 days ago
adapter_model.safetensors
2.68 GB
LFS
Training in progress, step 17
7 days ago
special_tokens_map.json
325 Bytes
Model save
about 2 months ago
tokenizer.json
9.09 MB
Training in progress, step 17
7 days ago
tokenizer_config.json
51 kB
Model save
about 2 months ago
training_args.bin
pickle
Detected Pickle imports (10)
"transformers.trainer_utils.IntervalStrategy"
,
"trl.trainer.dpo_config.FDivergenceType"
,
"trl.trainer.dpo_config.DPOConfig"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.training_args.OptimizerNames"
,
"torch.device"
,
"accelerate.state.PartialState"
How to fix it?
5.88 kB
LFS
Training in progress, step 17
7 days ago