qwen2
Improve language tag (
#1)
- 1.57 kB Add checkpoint-375: GRPO-trained corruption repair model
- 2.23 kB Improve language tag (#1)
- 605 Bytes Add checkpoint-375: GRPO-trained corruption repair model
- 742 Bytes Add checkpoint-375: GRPO-trained corruption repair model
- 138 Bytes Add checkpoint-375: GRPO-trained corruption repair model
- 1.67 MB Add checkpoint-375: GRPO-trained corruption repair model
- 4.88 GB Add checkpoint-375: GRPO-trained corruption repair model
- 4.93 GB Add checkpoint-375: GRPO-trained corruption repair model
- 4.33 GB Add checkpoint-375: GRPO-trained corruption repair model
- 1.09 GB Add checkpoint-375: GRPO-trained corruption repair model
- 27.8 kB Add checkpoint-375: GRPO-trained corruption repair model
- 616 Bytes Add checkpoint-375: GRPO-trained corruption repair model
- 11.4 MB Add checkpoint-375: GRPO-trained corruption repair model
- 4.74 kB Add checkpoint-375: GRPO-trained corruption repair model
- 155 kB Add checkpoint-375: GRPO-trained corruption repair model
training_args.bin Detected Pickle imports (14)
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.training_args.OptimizerNames",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_utils.SaveStrategy",
- "torch.device",
- "trl.trainer.grpo_config.GRPOConfig",
- "accelerate.state.PartialState"
How to fix it?
7.86 kB Add checkpoint-375: GRPO-trained corruption repair model - 2.78 MB Add checkpoint-375: GRPO-trained corruption repair model
