Update README.md
e29a106 verified - 1.66 kB Upload PLLuM_2512_chat_Public_Summary_of_Training_Content.pdf
- 394 kB Upload PLLuM_2512_chat_Public_Summary_of_Training_Content.pdf
- 17.9 kB Update README.md
- 76 Bytes Upload model and tokenizer
- 1.05 kB Upload model and tokenizer
- 2.55 kB Upload model and tokenizer
- 217 Bytes Upload model and tokenizer
- 4.96 GB Upload model and tokenizer
- 3.64 GB Upload model and tokenizer
- 90.6 kB Update model.safetensors.index.json
- 728 Bytes Upload model and tokenizer
- 33.4 MB Upload model and tokenizer
- 4.69 MB Upload model and tokenizer
- 1.16 MB Upload model and tokenizer
training_args.bin Detected Pickle imports (22)
- "collections.defaultdict",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "omegaconf.nodes.AnyNode",
- "__builtin__.dict",
- "transformers.trainer_utils.SchedulerType",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "accelerate.state.PartialState",
- "transformers.training_args.OptimizerNames",
- "omegaconf.base.Metadata",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "trl.trainer.dpo_config.DPOConfig",
- "typing.Any",
- "omegaconf.dictconfig.DictConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "omegaconf.base.ContainerMetadata",
- "torch.bfloat16",
- "trl.trainer.dpo_config.FDivergenceType"
How to fix it?
18.1 kB Upload model and tokenizer
