Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
alecwangcq
/
zephyr-7b-dpo-full-10-epochs-debug
like
0
Text Generation
Transformers
TensorBoard
mistral
conversational
Inference Endpoints
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
0ce026c
zephyr-7b-dpo-full-10-epochs-debug
1 contributor
History:
7 commits
This model has 1 file scanned as suspicious.
Show
files
alecwangcq
Training in progress, step 6000
0ce026c
11 months ago
runs
Training in progress, step 6000
11 months ago
.gitattributes
Safe
1.52 kB
initial commit
11 months ago
config.json
Safe
627 Bytes
Training in progress, step 3500
11 months ago
special_tokens_map.json
Safe
551 Bytes
Training in progress, step 3500
11 months ago
tokenizer.json
Safe
1.8 MB
Training in progress, step 3500
11 months ago
tokenizer_config.json
Safe
1.34 kB
Training in progress, step 3500
11 months ago
training_args.bin
Suspicious
pickle
Detected Pickle imports (11)
"alignment.configs.DPOConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"torch.device"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"accelerate.utils.dataclasses.DistributedType"
,
"accelerate.utils.deepspeed.HfDeepSpeedConfig"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.HubStrategy"
How to fix it?
5.69 kB
LFS
Training in progress, step 3500
11 months ago