Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Youliang
/
llama3-70b-instruct-lora-derta-100step
like
1
PEFT
Safetensors
Generated from Trainer
arxiv:
2407.09121
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
llama3-70b-instruct-lora-derta-100step
2.49 GB
1 contributor
History:
8 commits
This model has 1 file scanned as suspicious.
Show
files
Youliang
Update README.md
cccb915
verified
over 1 year ago
adapter_model
Upload 13 files
over 1 year ago
.gitattributes
Safe
1.52 kB
initial commit
over 1 year ago
README.md
Safe
2.04 kB
Update README.md
over 1 year ago
adapter_config.json
Safe
769 Bytes
Update adapter_config.json
over 1 year ago
adapter_model.safetensors
2.49 GB
xet
Upload adapter_model.safetensors
over 1 year ago
latest
Safe
14 Bytes
Upload 13 files
over 1 year ago
special_tokens_map.json
Safe
439 Bytes
Upload 13 files
over 1 year ago
tokenizer.json
Safe
9.09 MB
Upload 13 files
over 1 year ago
tokenizer_config.json
Safe
51.2 kB
Upload 13 files
over 1 year ago
trainer_state.json
Safe
2.06 kB
Upload 13 files
over 1 year ago
training_args.bin
Suspicious
pickle
Detected Pickle imports (13)
"torch.bfloat16"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.state.PartialState"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.training_args.OptimizerNames"
,
"__main__.LoRATrainingArguments"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"torch.device"
How to fix it?
7.54 kB
xet
Upload 13 files
over 1 year ago
zero_to_fp32.py
Safe
24.2 kB
Upload 13 files
over 1 year ago
