Update README.md
a3a16f2 verified - 1.57 kB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 2.86 kB Update README.md
- 605 Bytes Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 211 Bytes Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 733 Bytes Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 988 Bytes Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 242 Bytes Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 1.67 MB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 3.09 GB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 616 Bytes Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 11.4 MB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 7.34 kB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 211 Bytes Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 6.95 MB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 5.74 MB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
training_args.bin Detected Pickle imports (13)
- "transformers.trainer_utils.HubStrategy",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "accelerate.state.PartialState",
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "torch.bfloat16",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin"
How to fix it?
7.22 kB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b - 20.7 kB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
- 2.78 MB Import open-thoughts/OpenThinker3-1.5B as GRM-1.5b
