Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
jasonhuang3
/
Pro6000-llama3-2-1b-instruct-dpo-lora-28k
like
0
Transformers
Safetensors
Generated from Trainer
trl
dpo
arxiv:
2305.18290
Model card
Files
Files and versions
xet
Community
Train
Deploy
Use this model
2470cfb
Pro6000-llama3-2-1b-instruct-dpo-lora-28k
62.4 MB
1 contributor
History:
15 commits
jasonhuang3
Training in progress, step 7000
2470cfb
verified
about 1 month ago
.gitattributes
Safe
1.57 kB
Training in progress, step 500
about 1 month ago
adapter_config.json
Safe
944 Bytes
Training in progress, step 500
about 1 month ago
adapter_model.safetensors
45.1 MB
xet
Training in progress, step 7000
about 1 month ago
chat_template.jinja
Safe
3.83 kB
Training in progress, step 500
about 1 month ago
special_tokens_map.json
Safe
325 Bytes
Training in progress, step 500
about 1 month ago
tokenizer.json
Safe
17.2 MB
xet
Training in progress, step 500
about 1 month ago
tokenizer_config.json
Safe
50.6 kB
Training in progress, step 500
about 1 month ago
training_args.bin
pickle
Detected Pickle imports (11)
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.IntervalStrategy"
,
"trl.trainer.dpo_config.FDivergenceType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.SaveStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"trl.trainer.dpo_config.DPOConfig"
,
"transformers.training_args.OptimizerNames"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
6.8 kB
xet
Training in progress, step 500
about 1 month ago