winglian
/

zephyr-deita-kto-3ep-v3-r512-bsz8-alpha256

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-deita-kto-3ep-v3-r512-bsz8-alpha256

1 contributor

History: 2 commits

winglian's picture

End of training

d1300e2 verified 10 months ago

runs
End of training 10 months ago
.gitattributes

1.52 kB

initial commit 10 months ago
README.md

3.42 kB

End of training 10 months ago
adapter_config.json

664 Bytes

End of training 10 months ago
adapter_model.safetensors

2.68 GB
LFS

End of training 10 months ago
config.json

656 Bytes

End of training 10 months ago
generation_config.json

116 Bytes

End of training 10 months ago
model-00001-of-00004.safetensors

5 GB
LFS

End of training 10 months ago
model-00002-of-00004.safetensors

4.99 GB
LFS

End of training 10 months ago
model-00003-of-00004.safetensors

4.94 GB
LFS

End of training 10 months ago
model-00004-of-00004.safetensors

2.23 GB
LFS

End of training 10 months ago
model.safetensors.index.json

69.5 kB

End of training 10 months ago
special_tokens_map.json

624 Bytes

End of training 10 months ago
tokenizer.model

493 kB
LFS

End of training 10 months ago
tokenizer_config.json

1.53 kB

End of training 10 months ago
training_args.bin
Detected Pickle imports (8)
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.TrainingArguments",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames"
How to fix it?
4.35 kB
LFS

End of training 10 months ago