Update 8B/ README.MD
72b28a9 verified - 34 Bytes Update 8B/ README.MD
- 1.57 kB Rename .gitattributes to 8B/.gitattributes
- 873 Bytes Rename config.json to 8B/config.json
- 184 Bytes Rename generation_config.json to 8B/generation_config.json
- 0 Bytes Rename log.json to 8B/log.json
- 4.89 GB Rename pytorch_model-00001-of-00007.bin to 8B/pytorch_model-00001-of-00007.bin
- 4.83 GB Rename pytorch_model-00002-of-00007.bin to 8B/pytorch_model-00002-of-00007.bin
- 5 GB Rename pytorch_model-00003-of-00007.bin to 8B/pytorch_model-00003-of-00007.bin
- 5 GB Rename pytorch_model-00004-of-00007.bin to 8B/pytorch_model-00004-of-00007.bin
- 4.83 GB Rename pytorch_model-00005-of-00007.bin to 8B/pytorch_model-00005-of-00007.bin
- 5 GB Rename pytorch_model-00006-of-00007.bin to 8B/pytorch_model-00006-of-00007.bin
- 2.57 GB Rename pytorch_model-00007-of-00007.bin to 8B/pytorch_model-00007-of-00007.bin
- 24 kB Rename pytorch_model.bin.index.json to 8B/pytorch_model.bin.index.json
- 325 Bytes Rename special_tokens_map.json to 8B/special_tokens_map.json
- 17.2 MB Rename tokenizer.json to 8B/tokenizer.json
- 55.5 kB Rename tokenizer_config.json to 8B/tokenizer_config.json
training_args.bin Detected Pickle imports (14)
- "transformers.trainer_utils.SaveStrategy",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "torch.device",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "trl.trainer.grpo_config.GRPOConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_utils.HubStrategy",
- "torch.float32",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames"
How to fix it?
7.8 kB Rename training_args.bin to 8B/training_args.bin - 33.3 kB Rename zero_to_fp32.py to 8B/zero_to_fp32.py