Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
alignment-handbook
/
zephyr-7b-dpo-qlora
like
9
Follow
H4 Alignment Handbook
22
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
1
Train
Use this model
0cafdfb
zephyr-7b-dpo-qlora
2 contributors
History:
4 commits
lewtun
HF staff
Update README.md
0cafdfb
12 months ago
runs
Model save
12 months ago
.gitattributes
1.52 kB
initial commit
12 months ago
README.md
2.6 kB
Update README.md
12 months ago
adapter_config.json
520 Bytes
Model save
12 months ago
adapter_model.safetensors
218 MB
LFS
Model save
12 months ago
all_results.json
736 Bytes
Model save
12 months ago
config.json
614 Bytes
End of training
12 months ago
eval_results.json
561 Bytes
Model save
12 months ago
special_tokens_map.json
551 Bytes
Model save
12 months ago
tokenizer.json
1.8 MB
Model save
12 months ago
tokenizer_config.json
1.34 kB
Model save
12 months ago
train_results.json
195 Bytes
Model save
12 months ago
trainer_state.json
142 kB
Model save
12 months ago
training_args.bin
pickle
Detected Pickle imports (8)
"transformers.trainer_utils.SchedulerType"
,
"alignment.configs.DPOConfig"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.training_args.OptimizerNames"
,
"torch.device"
,
"accelerate.state.PartialState"
How to fix it?
4.73 kB
LFS
Model save
12 months ago