Boko99
/

Llama-3.2-3B-SFT-QLoRA

Text Generation

Generated from Trainer

alignment-handbook

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Llama-3.2-3B-SFT-QLoRA

Ctrl+K

Ctrl+K

2 contributors

History: 6 commits

ByungOh-Ko

Update model

468cae5 6 months ago

.gitattributes

113 Bytes

Update model 6 months ago
README.md

1.76 kB

Update model 6 months ago
adapter_config.json

797 Bytes

Update model 6 months ago
adapter_model.safetensors

97.3 MB
LFS

Update model 6 months ago
all_results.json

421 Bytes

Update model 6 months ago
config.json

1.41 kB

Update model 6 months ago
eval_results.json

204 Bytes

Update model 6 months ago
special_tokens_map.json

335 Bytes

Update model 6 months ago
tokenizer.json

17.2 MB
LFS

Update model 6 months ago
tokenizer_config.json

51 kB

Update model 6 months ago
train_results.json

252 Bytes

Update model 6 months ago
trainer_state.json

59.6 kB

Update model 6 months ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "alignment.configs.SFTConfig",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.SaveStrategy"
How to fix it?
5.75 kB

Update model 6 months ago