zd21
/

DeepSeek-TD2-PRM

Model card Files Files and versions

DeepSeek-TD2-PRM / checkpoint-5520

14.1 GB

1 contributor

History: 1 commit

zd21's picture

Upload folder using huggingface_hub

49b39d1 verified 7 months ago

config.json

924 Bytes

Upload folder using huggingface_hub 7 months ago
model-00001-of-00003.safetensors

4.87 GB
xet

Upload folder using huggingface_hub 7 months ago
model-00002-of-00003.safetensors

4.93 GB
xet

Upload folder using huggingface_hub 7 months ago
model-00003-of-00003.safetensors

4.33 GB
xet

Upload folder using huggingface_hub 7 months ago
model.safetensors.index.json

27.8 kB

Upload folder using huggingface_hub 7 months ago
tokenizer.json

7.03 MB

Upload folder using huggingface_hub 7 months ago
tokenizer_config.json

3.06 kB

Upload folder using huggingface_hub 7 months ago
trainer_state.json

968 kB

Upload folder using huggingface_hub 7 months ago
training_args.bin
Detected Pickle imports (13)
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.training_args.OptimizerNames",
- "torch.device",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "accelerate.state.PartialState",
- "torch.bfloat16",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "transformers.training_args.TrainingArguments",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
6.97 kB
xet

Upload folder using huggingface_hub 7 months ago