himanshunakrani9
/

TinyMathReason-1B-grpo

Model card Files Files and versions

TinyMathReason-1B-grpo

2.68 GB

Ctrl+K

Ctrl+K

1 contributor

History: 5 commits

himanshunakrani9's picture

himanshunakrani9

Upload folder using huggingface_hub

070e175 verified 13 days ago

eval_results
Upload folder using huggingface_hub 13 days ago
logs
Upload folder using huggingface_hub 13 days ago
.gitattributes

2.07 kB
Upload folder using huggingface_hub 13 days ago
README.md

3.25 kB
Update final benchmark results (GSM8K, Math, ARC, MMLU, HellaSwag) 13 days ago
chat_template.jinja

436 Bytes
Upload TinyMathReason-1B base model (1.126B params, bfloat16) 13 days ago
config.json

724 Bytes
Upload TinyMathReason-1B base model (1.126B params, bfloat16) 13 days ago
generation_config.json

148 Bytes
Upload TinyMathReason-1B base model (1.126B params, bfloat16) 13 days ago
model.safetensors

2.25 GB
xet

Upload TinyMathReason-1B base model (1.126B params, bfloat16) 13 days ago
tokenizer.json

2.25 MB
Upload TinyMathReason-1B base model (1.126B params, bfloat16) 13 days ago
tokenizer_config.json

294 Bytes
Upload TinyMathReason-1B base model (1.126B params, bfloat16) 13 days ago
training_args.bin
Detected Pickle imports (10)
- "accelerate.utils.dataclasses.DistributedType",
- "trl.trainer.grpo_config.GRPOConfig",
- "transformers.trainer_utils.SchedulerType",
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
7.31 kB
xet

Upload TinyMathReason-1B base model (1.126B params, bfloat16) 13 days ago