Update README.md
d6e5e3b verified - 1.57 kB Upload tokenizer.json with huggingface_hub
- 6.46 kB Update README.md
- 605 Bytes Upload added_tokens.json with huggingface_hub
- 1.05 kB Upload chat_template.json with huggingface_hub
- 1.32 kB Upload config.json with huggingface_hub
- 287 Bytes Upload generation_config.json with huggingface_hub
- 1.67 MB Upload merges.txt with huggingface_hub
- 5 GB Upload model-00001-of-00002.safetensors with huggingface_hub
- 2.51 GB Upload model-00002-of-00002.safetensors with huggingface_hub
- 65.4 kB Upload model.safetensors.index.json with huggingface_hub
- 578 Bytes Upload preprocessor_config.json with huggingface_hub
- 613 Bytes Upload special_tokens_map.json with huggingface_hub
- 11.4 MB Upload tokenizer.json with huggingface_hub
- 5.78 kB Upload tokenizer_config.json with huggingface_hub
- 312 kB Upload trainer_state.json with huggingface_hub
training_args.bin Detected Pickle imports (14)
- "accelerate.state.PartialState",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_utils.SchedulerType",
- "trl.trainer.grpo_config.GRPOConfig",
- "torch.bfloat16",
- "transformers.trainer_utils.SaveStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.device",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
8.44 kB Upload training_args.bin with huggingface_hub - 2.78 MB Upload vocab.json with huggingface_hub
