Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
huseyinatahaninan
/
phi-2-dpo
like
0
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
phi
alignment-handbook
Generated from Trainer
custom_code
License:
mit
Model card
Files
Files and versions
Community
1
Use this model
main
phi-2-dpo
1 contributor
History:
4 commits
huseyinatahaninan
Update README.md
e23c721
verified
11 months ago
.gitattributes
Safe
1.52 kB
initial commit
11 months ago
README.md
Safe
1.32 kB
Update README.md
11 months ago
adapter_config.json
Safe
647 Bytes
model
11 months ago
adapter_model.safetensors
Safe
252 MB
LFS
model
11 months ago
added_tokens.json
Safe
1.08 kB
model
11 months ago
all_results.json
Safe
195 Bytes
model
11 months ago
config.json
Safe
897 Bytes
model
11 months ago
merges.txt
Safe
456 kB
model
11 months ago
special_tokens_map.json
Safe
587 Bytes
model
11 months ago
tokenizer.json
Safe
2.11 MB
model
11 months ago
tokenizer_config.json
Safe
7.82 kB
model
11 months ago
train_results.json
Safe
195 Bytes
model
11 months ago
trainer_state.json
Safe
277 kB
model
11 months ago
training_args.bin
pickle
Detected Pickle imports (8)
"transformers.trainer_utils.SchedulerType"
,
"torch.device"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.HubStrategy"
,
"alignment.configs.DPOConfig"
,
"accelerate.state.PartialState"
How to fix it?
4.98 kB
LFS
model
11 months ago
vocab.json
Safe
798 kB
model
11 months ago