Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

NbAiLab
/
nynorsk_second_test_GRPO

Safetensors
llama
๐Ÿ‡ช๐Ÿ‡บ Region: EU
Model card Files Files and versions
xet
Community
nynorsk_second_test_GRPO
4.96 GB
  • 1 contributor
History: 2 commits
pere's picture
pere
GRPO model (assistant split heuristic reward)
78decbe verified 3 months ago
  • .gitattributes
    1.57 kB
    GRPO model (assistant split heuristic reward) 3 months ago
  • chat_template.jinja
    3.83 kB
    GRPO model (assistant split heuristic reward) 3 months ago
  • config.json
    888 Bytes
    GRPO model (assistant split heuristic reward) 3 months ago
  • generation_config.json
    241 Bytes
    GRPO model (assistant split heuristic reward) 3 months ago
  • model.safetensors
    4.94 GB
    xet
    GRPO model (assistant split heuristic reward) 3 months ago
  • special_tokens_map.json
    449 Bytes
    GRPO model (assistant split heuristic reward) 3 months ago
  • tokenizer.json
    17.2 MB
    xet
    GRPO model (assistant split heuristic reward) 3 months ago
  • tokenizer_config.json
    50.6 kB
    GRPO model (assistant split heuristic reward) 3 months ago
  • training_args.bin

    Detected Pickle imports (10)

    • "accelerate.state.PartialState",
    • "transformers.trainer_pt_utils.AcceleratorConfig",
    • "transformers.trainer_utils.SaveStrategy",
    • "transformers.training_args.OptimizerNames",
    • "transformers.trainer_utils.SchedulerType",
    • "trl.trainer.grpo_config.GRPOConfig",
    • "torch.device",
    • "transformers.trainer_utils.IntervalStrategy",
    • "accelerate.utils.dataclasses.DistributedType",
    • "transformers.trainer_utils.HubStrategy"

    How to fix it?

    6.46 kB
    xet
    GRPO model (assistant split heuristic reward) 3 months ago