TTTXXX01
/

zephyr-7b-Cal-DPO-SELM

alignment_handbook-handbook

Generated from Trainer

Model card Files Files and versions Community

zephyr-7b-Cal-DPO-SELM

2 contributors

History: 2 commits

Teng Xiao

TX

eaa81cf 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
README.md

1.41 kB

TX 3 months ago
all_results.json

231 Bytes

TX 3 months ago
config.json

654 Bytes

TX 3 months ago
generation_config.json

111 Bytes

TX 3 months ago
model-00001-of-00003.safetensors

4.94 GB
LFS

TX 3 months ago
model-00002-of-00003.safetensors

5 GB
LFS

TX 3 months ago
model-00003-of-00003.safetensors

4.54 GB
LFS

TX 3 months ago
model.safetensors.index.json

24 kB

TX 3 months ago
special_tokens_map.json

551 Bytes

TX 3 months ago
tokenizer.json

1.8 MB

TX 3 months ago
tokenizer_config.json

1.39 kB

TX 3 months ago
train_results.json

231 Bytes

TX 3 months ago
trainer_state.json

51.2 kB

TX 3 months ago
training_args.bin
Detected Pickle imports (14)
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.state.PartialState",
- "torch.bfloat16",
- "dpo_config.FDivergenceType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "accelerate.utils.dataclasses.DistributedType",
- "dpo_config.DPOConfig",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames"
How to fix it?
7.16 kB
LFS

TX 3 months ago