2nji
/

sft_qlora_Meta-Llama-3.1-8B

Generated from Trainer

Model card Files Files and versions

sft_qlora_Meta-Llama-3.1-8B

101 MB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

2nji's picture

Saving model and tokenizer

cf1c573 verified about 1 year ago

.gitattributes

1.57 kB
Training in progress, step 500 about 1 year ago
README.md

1.76 kB
Saving model and tokenizer about 1 year ago
adapter_config.json

816 Bytes
Training in progress, step 500 about 1 year ago
adapter_model.safetensors

83.9 MB
xet

Saving model and tokenizer about 1 year ago
special_tokens_map.json

459 Bytes
Training in progress, step 500 about 1 year ago
tokenizer.json

17.2 MB
xet

Training in progress, step 500 about 1 year ago
tokenizer_config.json

50.6 kB
Training in progress, step 500 about 1 year ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "UnslothSFTTrainer.UnslothSFTConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.training_args.OptimizerNames",
- "torch.device"
How to fix it?
5.69 kB
xet

Training in progress, step 500 about 1 year ago