JakeOh
/

llama-3.2-1b-gsm8k-step-0-sft

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

llama-3.2-1b-gsm8k-step-0-sft

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

JakeOh's picture

Model save

0cfdb7d verified 1 day ago

.gitattributes

1.57 kB

Model save 1 day ago
README.md

1.71 kB

Model save 1 day ago
chat_template.jinja

493 Bytes

Model save 1 day ago
config.json

838 Bytes

Model save 1 day ago
generation_config.json

180 Bytes

Model save 1 day ago
model.safetensors

2.47 GB
LFS

Model save 1 day ago
special_tokens_map.json

335 Bytes

Model save 1 day ago
tokenizer.json

17.2 MB
LFS

Model save 1 day ago
tokenizer_config.json

50.6 kB

Model save 1 day ago
training_args.bin
Detected Pickle imports (10)
- "torch.device",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.HubStrategy",
- "revise.args.sft.SFTConfig",
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.OptimizerNames"
How to fix it?
6.29 kB
LFS

Model save 1 day ago