RedaAlami
/

zephyr-7b-gemma-dpo

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-gemma-dpo

1 contributor

History: 5 commits

RedaAlami's picture

End of training

3a9c5a4 verified 4 months ago

runs
End of training 4 months ago
.gitattributes

1.57 kB

Model save 4 months ago
README.md

3.26 kB

End of training 4 months ago
adapter_config.json

743 Bytes

Model save 4 months ago
adapter_model.safetensors

800 MB
LFS

Model save 4 months ago
all_results.json

783 Bytes

End of training 4 months ago
config.json

1.21 kB

End of training 4 months ago
eval_results.json

587 Bytes

End of training 4 months ago
special_tokens_map.json

630 Bytes

Model save 4 months ago
tokenizer.json

17.5 MB
LFS

Model save 4 months ago
tokenizer_config.json

1.89 kB

Model save 4 months ago
train_results.json

231 Bytes

Model save 4 months ago
trainer_state.json

39.4 kB

Model save 4 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "alignment.configs.DPOConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
5.43 kB
LFS

Model save 4 months ago