sayakpaul
/

gemma-2b-sft-qlora-no-robots

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

gemma-2b-sft-qlora-no-robots

1 contributor

History: 2 commits

sayakpaul's picture

sayakpaul HF staff

Model save

812699f verified 10 months ago

runs
Model save 10 months ago
.gitattributes

1.57 kB

Model save 10 months ago
README.md

1.54 kB

Model save 10 months ago
adapter_config.json

645 Bytes

Model save 10 months ago
adapter_model.safetensors

100 MB
LFS

Model save 10 months ago
all_results.json

189 Bytes

Model save 10 months ago
special_tokens_map.json

557 Bytes

Model save 10 months ago
tokenizer.json

17.5 MB
LFS

Model save 10 months ago
tokenizer_config.json

1.75 kB

Model save 10 months ago
train_results.json

189 Bytes

Model save 10 months ago
trainer_state.json

1.03 kB

Model save 10 months ago
training_args.bin
Detected Pickle imports (9)
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SchedulerType",
- "alignment.configs.SFTConfig",
- "accelerate.state.PartialState",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames"
How to fix it?
5.05 kB
LFS

Model save 10 months ago