Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
dball
/
zephyr-7b-dpo-qlora-no-sft
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
1
Train
Use this model
a8d6cf5
zephyr-7b-dpo-qlora-no-sft
1 contributor
History:
2 commits
dball
Training in progress, step 200
a8d6cf5
verified
7 months ago
runs
Training in progress, step 200
7 months ago
.gitattributes
1.52 kB
initial commit
7 months ago
adapter_config.json
655 Bytes
Training in progress, step 200
7 months ago
adapter_model.safetensors
83.9 MB
LFS
Training in progress, step 200
7 months ago
special_tokens_map.json
437 Bytes
Training in progress, step 200
7 months ago
tokenizer.json
1.8 MB
Training in progress, step 200
7 months ago
tokenizer.model
493 kB
LFS
Training in progress, step 200
7 months ago
tokenizer_config.json
942 Bytes
Training in progress, step 200
7 months ago
training_args.bin
pickle
Detected Pickle imports (8)
"torch.device"
,
"alignment.configs.DPOConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
How to fix it?
4.92 kB
LFS
Training in progress, step 200
7 months ago