Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
shenxq
/
zephyr-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
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
6bf8544
zephyr-7b-dpo-qlora
1 contributor
History:
3 commits
shenxq
Training in progress, step 100
6bf8544
verified
6 months ago
runs
Training in progress, step 100
6 months ago
.gitattributes
1.52 kB
initial commit
6 months ago
adapter_config.json
655 Bytes
Training in progress, step 100
6 months ago
adapter_model.safetensors
168 MB
LFS
Training in progress, step 100
6 months ago
special_tokens_map.json
437 Bytes
Training in progress, step 100
6 months ago
tokenizer.json
1.8 MB
Training in progress, step 100
6 months ago
tokenizer.model
493 kB
LFS
Training in progress, step 100
6 months ago
tokenizer_config.json
1.39 kB
Training in progress, step 100
6 months ago
training_args.bin
pickle
Detected Pickle imports (8)
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
,
"torch.device"
,
"alignment.configs.DPOConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
How to fix it?
5.18 kB
LFS
Training in progress, step 100
6 months ago