jspr
/

bts_mistral_7b_v3_32k_LoRA

Generated from Trainer

8-bit precision

Model card Files Files and versions

bts_mistral_7b_v3_32k_LoRA

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

jspr's picture

End of training

02299d0 verified over 1 year ago

.gitattributes

1.52 kB

initial commit over 1 year ago
README.md

3.59 kB

End of training over 1 year ago
adapter_config.json

620 Bytes

End of training over 1 year ago
adapter_model.bin

13.7 MB
xet

End of training over 1 year ago
adapter_model.safetensors

13.6 MB
xet

End of training over 1 year ago
ax_config.yaml

1.41 kB

Create ax_config.yaml over 1 year ago
config.json

1.16 kB

End of training over 1 year ago
special_tokens_map.json

437 Bytes

End of training over 1 year ago
tokenizer.model

493 kB
xet

End of training over 1 year ago
tokenizer_config.json

1.02 kB

End of training over 1 year ago
training_args.bin
Detected Pickle imports (9)
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.state.PartialState",
- "axolotl.core.trainer_builder.AxolotlTrainingArguments",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType"
How to fix it?
5.56 kB
xet

End of training over 1 year ago