Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jikaixuan
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
1b1d13d
zephyr-7b-dpo-qlora
1 contributor
History:
18 commits
This model has 1 file scanned as suspicious.
Show
files
jikaixuan
End of training
1b1d13d
verified
8 months ago
runs
Training in progress, step 100
9 months ago
.gitattributes
Safe
1.52 kB
initial commit
9 months ago
README.md
Safe
2.9 kB
End of training
8 months ago
adapter_config.json
Safe
657 Bytes
Model save
8 months ago
adapter_model.safetensors
Safe
671 MB
LFS
Model save
8 months ago
all_results.json
Safe
745 Bytes
Model save
8 months ago
config.json
Safe
1.03 kB
End of training
8 months ago
eval_results.json
Safe
571 Bytes
Model save
8 months ago
special_tokens_map.json
Safe
551 Bytes
Training in progress, step 100
9 months ago
tokenizer.json
Safe
1.8 MB
Training in progress, step 100
9 months ago
tokenizer_config.json
Safe
1.39 kB
Training in progress, step 200
8 months ago
train_results.json
Safe
194 Bytes
Model save
8 months ago
trainer_state.json
Safe
26.2 kB
Model save
8 months ago
training_args.bin
Suspicious
pickle
Detected Pickle imports (8)
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.state.PartialState"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_utils.HubStrategy"
,
"torch.device"
,
"alignment.configs.DPOConfig"
How to fix it?
4.92 kB
LFS
Model save
8 months ago