BenGyi
/

rtg-llama-lora

Text Generation

defect-detection

Model card Files Files and versions

71.8 MB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

BenGyi's picture

Initial upload: Llama 3.1-8B LoRA r=16 adapter (3-epoch SFT on rail defect reports)

bc7f9b7 verified 11 days ago

.gitattributes

1.57 kB
Initial upload: Llama 3.1-8B LoRA r=16 adapter (3-epoch SFT on rail defect reports) 11 days ago
README.md

3.37 kB
Add model card 11 days ago
adapter_config.json

1.07 kB
Initial upload: Llama 3.1-8B LoRA r=16 adapter (3-epoch SFT on rail defect reports) 11 days ago
adapter_model.safetensors

54.6 MB
xet

Initial upload: Llama 3.1-8B LoRA r=16 adapter (3-epoch SFT on rail defect reports) 11 days ago
chat_template.jinja

348 Bytes
Initial upload: Llama 3.1-8B LoRA r=16 adapter (3-epoch SFT on rail defect reports) 11 days ago
tokenizer.json

17.2 MB
xet

Initial upload: Llama 3.1-8B LoRA r=16 adapter (3-epoch SFT on rail defect reports) 11 days ago
tokenizer_config.json

369 Bytes
Initial upload: Llama 3.1-8B LoRA r=16 adapter (3-epoch SFT on rail defect reports) 11 days ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.state.PartialState",
- "trl.trainer.sft_config.SFTConfig",
- "transformers.trainer_utils.SaveStrategy",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy"
How to fix it?
5.78 kB
xet

Initial upload: Llama 3.1-8B LoRA r=16 adapter (3-epoch SFT on rail defect reports) 11 days ago