Update README.md
f96df14 verified - checkpoint-500 Upload DPO fine-tuned Qwen model
- 1.64 kB Upload DPO fine-tuned Qwen model
- 877 Bytes Update README.md
- 876 Bytes Upload DPO fine-tuned Qwen model
- 61.4 MB Upload DPO fine-tuned Qwen model
- 707 Bytes Upload DPO fine-tuned Qwen model
- 4.17 kB Upload DPO fine-tuned Qwen model
- 1.67 MB Upload DPO fine-tuned Qwen model
- 496 Bytes Upload DPO fine-tuned Qwen model
- 11.4 MB Upload DPO fine-tuned Qwen model
- 5.4 kB Upload DPO fine-tuned Qwen model
training_args.bin Detected Pickle imports (11)
- "trl.trainer.dpo_config.DPOConfig",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "torch.device",
- "trl.trainer.dpo_config.FDivergenceType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy"
How to fix it?
6.87 kB Upload DPO fine-tuned Qwen model - 2.78 MB Upload DPO fine-tuned Qwen model
