Joe253
/

LessProblems_gpt2_dpo-sft-pretrainedlora_d-30k_e-10_causal-ans

Model card Files Files and versions Community

LessProblems_gpt2_dpo-sft-pretrainedlora_d-30k_e-10_causal-ans

1 contributor

History: 2 commits

Joe253's picture

Upload 9 files

d911910 verified 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
README.md

5.28 kB

Upload 9 files 3 months ago
adapter_config.json

656 Bytes

Upload 9 files 3 months ago
adapter_model.safetensors

3.25 MB
LFS

Upload 9 files 3 months ago
merges.txt

506 kB

Upload 9 files 3 months ago
special_tokens_map.json

494 Bytes

Upload 9 files 3 months ago
tokenizer.json

2.21 MB

Upload 9 files 3 months ago
tokenizer_config.json

496 Bytes

Upload 9 files 3 months ago
training_args.bin
Detected Pickle imports (9)
- "transformers.training_args.OptimizerNames",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "transformers.training_args.TrainingArguments",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SchedulerType"
How to fix it?
4.98 kB
LFS

Upload 9 files 3 months ago
vocab.json

798 kB

Upload 9 files 3 months ago