liuylhf
/

parallel-call-original-4-epoch-mixtral-8x22b-instruct

Generated from Trainer

Model card Files Files and versions Community

parallel-call-original-4-epoch-mixtral-8x22b-instruct

1 contributor

History: 9 commits

This model has one file that has been marked as unsafe.

View unsafe files

training_args.bin

liuylhf's picture

Model save

dda1a11 verified 5 months ago

.gitattributes

1.52 kB

initial commit 5 months ago
README.md

3.53 kB

Model save 5 months ago
adapter_config.json

661 Bytes

Training in progress, step 25 5 months ago
adapter_model.safetensors

279 MB
LFS

Model save 5 months ago
config.json

776 Bytes

Training in progress, step 25 5 months ago
special_tokens_map.json

434 Bytes

Training in progress, step 25 5 months ago
tokenizer.model

493 kB
LFS

Training in progress, step 25 5 months ago
tokenizer_config.json

1.51 kB

Training in progress, step 25 5 months ago
training_args.bin
Detected Pickle imports (9)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "accelerate.state.PartialState",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "transformers.trainer_utils.HubStrategy",
- "axolotl.core.trainer_builder.AxolotlTrainingArguments"
How to fix it?
6.07 kB
LFS

Training in progress, step 25 5 months ago