Update README.md
59848a4 verified - 1.52 kB initial commit
- 3.45 kB Update README.md
- 865 Bytes Upload adapter_config.json to model checkpoint
- 269 MB Upload adapter_model.safetensors to model checkpoint
- 67 Bytes Upload additional_config.json to model checkpoint
- 21.6 kB Upload args.json to model checkpoint
- 376 Bytes Create config.json
- 14 Bytes Upload latest to model checkpoint
rng_state_0.pth Detected Pickle imports (7)
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict",
- "torch.ByteStorage",
- "_codecs.encode",
- "numpy.core.multiarray._reconstruct",
- "torch._utils._rebuild_tensor_v2"
How to fix it?
15.4 kB Upload rng_state_0.pth to model checkpoint rng_state_1.pth Detected Pickle imports (7)
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict",
- "torch.ByteStorage",
- "_codecs.encode",
- "numpy.core.multiarray._reconstruct",
- "torch._utils._rebuild_tensor_v2"
How to fix it?
15.5 kB Upload rng_state_1.pth to model checkpoint rng_state_2.pth Detected Pickle imports (7)
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict",
- "torch.ByteStorage",
- "_codecs.encode",
- "numpy.core.multiarray._reconstruct",
- "torch._utils._rebuild_tensor_v2"
How to fix it?
15.5 kB Upload rng_state_2.pth to model checkpoint rng_state_3.pth Detected Pickle imports (7)
- "numpy.ndarray",
- "numpy.dtype",
- "collections.OrderedDict",
- "torch.ByteStorage",
- "_codecs.encode",
- "numpy.core.multiarray._reconstruct",
- "torch._utils._rebuild_tensor_v2"
How to fix it?
15.5 kB Upload rng_state_3.pth to model checkpoint - 1.06 kB Upload scheduler.pt to model checkpoint
- 27.8 kB Upload trainer_state.json to model checkpoint
training_args.bin Detected Pickle imports (14)
- "torch.device",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.HubStrategy",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "swift.trainers.rlhf_arguments.GRPOConfig",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
9.4 kB Upload training_args.bin to model checkpoint - 25.3 kB Upload zero_to_fp32.py to model checkpoint
