DrishtiSharma
/

llama2-7b-int4-dolly-15k-hindi-flash-attention2-w-packing

Generated from Trainer

Model card Files Files and versions Community

llama2-7b-int4-dolly-15k-hindi-flash-attention2-w-packing

1 contributor

History: 4 commits

DrishtiSharma's picture

Update README.md

0f23fb1 verified 5 months ago

.gitattributes

1.52 kB

initial commit 5 months ago
README.md

2.54 kB

Update README.md 5 months ago
adapter_config.json

629 Bytes

End of training 5 months ago
adapter_model.safetensors

268 MB
LFS

End of training 5 months ago
special_tokens_map.json

434 Bytes

End of training 5 months ago
tokenizer.json

1.84 MB

End of training 5 months ago
tokenizer_config.json

890 Bytes

End of training 5 months ago
training_args.bin
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 5 months ago