eastjin
/

tinyllama-sft-ko-qlora_v2

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Community

tinyllama-sft-ko-qlora_v2

1 contributor

History: 3 commits

eastjin's picture

End of training

0b62c0f verified 10 months ago

.gitattributes

1.52 kB

initial commit 10 months ago
README.md

1.84 kB

End of training 10 months ago
adapter_config.json

704 Bytes

Model save 10 months ago
adapter_model.safetensors

50.5 MB
LFS

Model save 10 months ago
all_results.json

357 Bytes

Model save 10 months ago
config.json

1.15 kB

End of training 10 months ago
eval_results.json

184 Bytes

Model save 10 months ago
special_tokens_map.json

437 Bytes

Model save 10 months ago
tokenizer.json

1.84 MB

Model save 10 months ago
tokenizer_config.json

893 Bytes

Model save 10 months ago
train_results.json

193 Bytes

Model save 10 months ago
trainer_state.json

118 kB

Model save 10 months ago
training_args.bin
Detected Pickle imports (9)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "alignment.configs.SFTConfig"
How to fix it?
4.98 kB
LFS

Model save 10 months ago