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

  • Log In
  • Sign Up

chchen
/
Ministral-8B-Instruct-2410-ppo-1000

PEFT
Safetensors
Model card Files Files and versions Community
Ministral-8B-Instruct-2410-ppo-1000
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
chchen's picture
chchen
Upload 13 files
e29bf33 verified 7 months ago
  • .gitattributes
    1.57 kB
    Upload 13 files 7 months ago
  • README.md
    5.11 kB
    Upload 13 files 7 months ago
  • adapter_config.json
    737 Bytes
    Upload 13 files 7 months ago
  • adapter_model.safetensors
    87.4 MB
    LFS
    Upload 13 files 7 months ago
  • llama3_lora_ppo.yaml
    897 Bytes
    Upload 13 files 7 months ago
  • special_tokens_map.json
    437 Bytes
    Upload 13 files 7 months ago
  • tokenizer.json
    17.1 MB
    LFS
    Upload 13 files 7 months ago
  • tokenizer_config.json
    181 kB
    Upload 13 files 7 months ago
  • trainer_log.jsonl
    5.93 kB
    Upload 13 files 7 months ago
  • trainer_state.json
    4.93 kB
    Upload 13 files 7 months ago
  • training_args.bin

    Detected Pickle imports (9)

    • "llamafactory.hparams.training_args.TrainingArguments",
    • "transformers.trainer_utils.IntervalStrategy",
    • "transformers.trainer_utils.HubStrategy",
    • "transformers.trainer_pt_utils.AcceleratorConfig",
    • "accelerate.state.PartialState",
    • "accelerate.utils.dataclasses.DistributedType",
    • "transformers.trainer_utils.SchedulerType",
    • "transformers.training_args.OptimizerNames",
    • "torch.device"

    How to fix it?

    5.62 kB
    LFS
    Upload 13 files 7 months ago
  • training_loss.png
    33.4 kB
    Upload 13 files 7 months ago
  • training_reward.png
    38 kB
    Upload 13 files 7 months ago
  • value_head.safetensors
    16.6 kB
    LFS
    Upload 13 files 7 months ago