Update README.md
ab6266a verified - 1.52 kB initial commit
- 6.61 kB Update README.md
- 1.08 kB upload added_tokens.json
- 1.42 kB upload config.json
- 9.26 kB upload configuration_phi.py
- 74 Bytes upload generation_config.json
- 9.71 kB upload generation_utils.py
- 23.2 kB upload llava_arch.py
- 456 kB upload merges.txt
- 5 GB upload model-00001-of-00002.safetensors
- 1.19 GB upload model-00002-of-00002.safetensors
- 84.9 kB upload model.safetensors.index.json
- 9.3 kB upload modeling_llava_phi.py
- 62.9 kB upload modeling_phi.py
- 473 Bytes upload special_tokens_map.json
- 2.11 MB upload tokenizer.json
- 7.37 kB upload tokenizer_config.json
- 1.44 MB upload trainer_state.json
training_args.bin Detected Pickle imports (11)
- "transformers.training_args.OptimizerNames",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SchedulerType",
- "torch.device",
- "torch.bfloat16",
- "llava.train.train.TrainingArguments",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
How to fix it?
6.78 kB upload training_args.bin - 98.5 kB Upload training_datasets_by_stage.jpg
- 798 kB upload vocab.json
