Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
aengusl
/
llama2-7b-sft-lora
like
0
PEFT
TensorBoard
Safetensors
generator
trl
sft
Generated from Trainer
License:
llama2
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
d8cfeaa
llama2-7b-sft-lora
1 contributor
History:
119 commits
aengusl
Training in progress, step 80
d8cfeaa
verified
5 months ago
runs
Training in progress, step 80
5 months ago
step_0
Training in progress, step 40
5 months ago
step_400
Training in progress, step 200
5 months ago
step_800
Model save
5 months ago
.gitattributes
1.52 kB
initial commit
5 months ago
README.md
1.55 kB
Training in progress, step 40
5 months ago
adapter_config.json
556 Bytes
Training in progress, step 40
5 months ago
adapter_model.safetensors
258 MB
LFS
Training in progress, step 80
5 months ago
special_tokens_map.json
437 Bytes
Model save
5 months ago
tokenizer.json
1.84 MB
Model save
5 months ago
tokenizer.model
pickle
500 kB
LFS
Model save
5 months ago
tokenizer_config.json
1.72 kB
Model save
5 months ago
training_args.bin
pickle
Detected Pickle imports (12)
"accelerate.state.PartialState"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"alignment.configs.SFTConfig"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.HubStrategy"
,
"torch.device"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"torch.bfloat16"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_utils.IntervalStrategy"
How to fix it?
6.2 kB
LFS
Training in progress, step 40
5 months ago