Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

IeBoytsov
/
llama-3-1-sft-qlora-debug

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Files and versions
xet
Metrics Training metrics Community

Instructions to use IeBoytsov/llama-3-1-sft-qlora-debug with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use IeBoytsov/llama-3-1-sft-qlora-debug with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B")
    model = PeftModel.from_pretrained(base_model, "IeBoytsov/llama-3-1-sft-qlora-debug")
  • Notebooks
  • Google Colab
  • Kaggle
llama-3-1-sft-qlora-debug
185 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 8 commits
IeBoytsov's picture
IeBoytsov
End of training
2faa422 verified almost 2 years ago
  • runs
    Model save almost 2 years ago
  • .gitattributes
    1.57 kB
    Training in progress, step 100 almost 2 years ago
  • README.md
    1.34 kB
    End of training almost 2 years ago
  • adapter_config.json
    726 Bytes
    Model save almost 2 years ago
  • adapter_model.safetensors
    168 MB
    xet
    Training in progress, step 75 almost 2 years ago
  • all_results.json
    233 Bytes
    Model save almost 2 years ago
  • config.json
    1.37 kB
    Model save almost 2 years ago
  • special_tokens_map.json
    335 Bytes
    Training in progress, step 100 almost 2 years ago
  • tokenizer.json
    17.2 MB
    xet
    Training in progress, step 100 almost 2 years ago
  • tokenizer_config.json
    51 kB
    Training in progress, step 100 almost 2 years ago
  • train_results.json
    233 Bytes
    Model save almost 2 years ago
  • trainer_state.json
    3.73 kB
    Model save almost 2 years ago
  • training_args.bin

    Detected Pickle imports (10)

    • "accelerate.utils.dataclasses.DistributedType",
    • "transformers.trainer_utils.SchedulerType",
    • "accelerate.state.PartialState",
    • "torch.device",
    • "transformers.trainer_utils.HubStrategy",
    • "transformers.trainer_utils.IntervalStrategy",
    • "transformers.trainer_pt_utils.AcceleratorConfig",
    • "transformers.utils.quantization_config.QuantizationMethod",
    • "transformers.training_args.OptimizerNames",
    • "alignment.configs.SFTConfig"

    How to fix it?

    6.26 kB
    xet
    Model save almost 2 years ago