Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
clembench-playpen
/
Llama-3.1-70B_KTO_noSFT
like
0
Follow
clembench-project-playpen
17
Transformers
Safetensors
Generated from Trainer
unsloth
trl
kto
arxiv:
2402.01306
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
Llama-3.1-70B_KTO_noSFT
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
mazzaqq
End of training
18c9307
verified
about 2 months ago
.gitattributes
Safe
1.57 kB
End of training
about 2 months ago
README.md
Safe
2.18 kB
End of training
about 2 months ago
adapter_config.json
Safe
804 Bytes
End of training
about 2 months ago
adapter_model.safetensors
3.31 GB
LFS
End of training
about 2 months ago
special_tokens_map.json
Safe
340 Bytes
End of training
about 2 months ago
tokenizer.json
Safe
17.2 MB
LFS
End of training
about 2 months ago
tokenizer_config.json
Safe
55.4 kB
End of training
about 2 months ago
training_args.bin
pickle
Detected Pickle imports (9)
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"torch.device"
,
"accelerate.state.PartialState"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.HubStrategy"
,
"trl.trainer.kto_config.KTOConfig"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
5.69 kB
LFS
End of training
about 2 months ago
