Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
lewtun
/
handbook-sft-qlora-test
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
mistral
alignment-handbook
Generated from Trainer
trl
sft
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
main
handbook-sft-qlora-test
1 contributor
History:
3 commits
lewtun
HF staff
End of training
2cadffe
10 months ago
runs
Model save
10 months ago
.gitattributes
Safe
1.52 kB
initial commit
10 months ago
README.md
Safe
1.65 kB
End of training
10 months ago
adapter_config.json
Safe
655 Bytes
Model save
10 months ago
adapter_model.safetensors
Safe
83.9 MB
LFS
Model save
10 months ago
all_results.json
Safe
361 Bytes
Model save
10 months ago
config.json
Safe
1.03 kB
End of training
10 months ago
eval_results.json
Safe
188 Bytes
Model save
10 months ago
special_tokens_map.json
Safe
437 Bytes
Model save
10 months ago
tokenizer.json
Safe
1.8 MB
Model save
10 months ago
tokenizer_config.json
Safe
1.39 kB
Model save
10 months ago
train_results.json
Safe
193 Bytes
Model save
10 months ago
trainer_state.json
Safe
1.02 kB
Model save
10 months ago
training_args.bin
pickle
Detected Pickle imports (8)
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.training_args.OptimizerNames"
,
"torch.device"
,
"alignment.configs.SFTConfig"
How to fix it?
4.73 kB
LFS
Model save
10 months ago