nnheui
/

zephyr-7b-kto-qlora

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-kto-qlora

1 contributor

History: 2 commits

nnheui's picture

Model save

b0b7528 verified 11 months ago

runs
Model save 11 months ago
.gitattributes

1.52 kB

initial commit 11 months ago
README.md

1.29 kB

Model save 11 months ago
adapter_config.json

669 Bytes

Model save 11 months ago
adapter_model.safetensors

671 MB
LFS

Model save 11 months ago
all_results.json

189 Bytes

Model save 11 months ago
special_tokens_map.json

551 Bytes

Model save 11 months ago
tokenizer.json

1.8 MB

Model save 11 months ago
tokenizer_config.json

1.39 kB

Model save 11 months ago
train_results.json

189 Bytes

Model save 11 months ago
trainer_state.json

1.16 kB

Model save 11 months ago
training_args.bin
Detected Pickle imports (9)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "alignment.configs.DPOConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.state.PartialState",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "transformers.trainer_utils.HubStrategy"
How to fix it?
5.11 kB
LFS

Model save 11 months ago