- 1.52 kB initial commit
- 9.03 kB add results table (#7)
- 434 Bytes Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint
- 716 Bytes Update config.json
- 222 Bytes Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint
- 121 Bytes Upload LlamaForCausalLM
- 4.99 GB Upload LlamaForCausalLM
- 4.98 GB Upload LlamaForCausalLM
- 3.85 GB Upload LlamaForCausalLM
- 22.5 kB Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint
- 482 Bytes Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint
- 43.3 kB Upload thumbnail.png
- 4.61 MB Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint
- 1.23 kB Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint
- 232 Bytes Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint
- 243 kB Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint
training_args.bin Detected Pickle imports (13)
- "torch.device",
- "transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig",
- "h4.training.configs.sft_config.SFTConfig",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "torch.bfloat16",
- "transformers.integrations.deepspeed.HfDeepSpeedConfig",
- "transformers.trainer_utils.SchedulerType",
- "accelerate.utils.dataclasses.DeepSpeedPlugin",
- "transformers.training_args.OptimizerNames",
- "accelerate.state.PartialState",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "accelerate.utils.dataclasses.DistributedType"
How to fix it?
6.71 kB Add AI-MO/deepseek-math-7b-sft-aimo_v51.2 checkpoint
