Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
DrishtiSharma
/
llama2-7b-int4-dolly-15k-hindi-flash-attention2-w-packing
like
0
PEFT
Safetensors
kpriyanshu256/databricks-dolly-15k-hi
trl
sft
Generated from Trainer
Model card
Files
Files and versions
Community
Use this model
main
llama2-7b-int4-dolly-15k-hindi-flash-attention2-w-packing
1 contributor
History:
4 commits
DrishtiSharma
Update README.md
0f23fb1
verified
8 months ago
.gitattributes
1.52 kB
initial commit
8 months ago
README.md
2.54 kB
Update README.md
8 months ago
adapter_config.json
629 Bytes
End of training
8 months ago
adapter_model.safetensors
268 MB
LFS
End of training
8 months ago
special_tokens_map.json
434 Bytes
End of training
8 months ago
tokenizer.json
1.84 MB
End of training
8 months ago
tokenizer_config.json
890 Bytes
End of training
8 months ago
training_args.bin
pickle
Detected Pickle imports (8)
"transformers.trainer_utils.SchedulerType"
,
"transformers.training_args.TrainingArguments"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.training_args.OptimizerNames"
,
"torch.device"
How to fix it?
4.79 kB
LFS
End of training
8 months ago