Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Samhita
/
OrpoLlama-3-8B-Instruct-Copy
like
0
PEFT
Safetensors
trl
orpo
Generated from Trainer
License:
llama3
Model card
Files
Files and versions
Community
Use this model
aa5ff0f
OrpoLlama-3-8B-Instruct-Copy
1 contributor
History:
4 commits
Samhita
Added non-lora keys as a separate file
aa5ff0f
verified
5 months ago
.gitattributes
Safe
1.52 kB
initial commit
5 months ago
README.md
Safe
3.04 kB
End of training
5 months ago
adapter_config.json
Safe
738 Bytes
End of training
5 months ago
adapter_model.safetensors
Safe
168 MB
LFS
Updated adapter_model with non-lora keys removed
5 months ago
rest.safetensors
Safe
4.2 GB
LFS
Added non-lora keys as a separate file
5 months ago
special_tokens_map.json
Safe
419 Bytes
End of training
5 months ago
tokenizer.json
Safe
9.09 MB
End of training
5 months ago
tokenizer_config.json
Safe
51.2 kB
End of training
5 months ago
training_args.bin
pickle
Detected Pickle imports (9)
"transformers.training_args.OptimizerNames"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.SchedulerType"
,
"torch.device"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"trl.trainer.orpo_config.ORPOConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.HubStrategy"
How to fix it?
5.43 kB
LFS
End of training
5 months ago