Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DUAL-GPO
/
zephyr-7b-gpo-iter1
like
0
PEFT
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
Generated from Trainer
trl
dpo
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Use this model
883507a
zephyr-7b-gpo-iter1
1 contributor
History:
2 commits
lole25
Training in progress, step 100
883507a
verified
5 months ago
.gitattributes
1.52 kB
initial commit
5 months ago
adapter_config.json
657 Bytes
Training in progress, step 100
5 months ago
adapter_model.safetensors
671 MB
LFS
Training in progress, step 100
5 months ago
special_tokens_map.json
551 Bytes
Training in progress, step 100
5 months ago
tokenizer.json
1.8 MB
Training in progress, step 100
5 months ago
tokenizer_config.json
1.39 kB
Training in progress, step 100
5 months ago
training_args.bin
pickle
Detected Pickle imports (11)
"torch.device"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"alignment.configs.DPOConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.state.PartialState"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"transformers.training_args.OptimizerNames"
,
"torch.bfloat16"
How to fix it?
5.82 kB
LFS
Training in progress, step 100
5 months ago