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

Ap98
/
zephyr-7b-sft-qlora

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

Instructions to use Ap98/zephyr-7b-sft-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use Ap98/zephyr-7b-sft-qlora with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
    model = PeftModel.from_pretrained(base_model, "Ap98/zephyr-7b-sft-qlora")
  • Notebooks
  • Google Colab
  • Kaggle
zephyr-7b-sft-qlora
86.3 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
Ap98's picture
Ap98
Model save
f2fbbd5 verified about 2 years ago
  • runs
    Model save about 2 years ago
  • .gitattributes
    1.52 kB
    initial commit about 2 years ago
  • README.md
    1.5 kB
    Model save about 2 years ago
  • adapter_config.json
    728 Bytes
    Model save about 2 years ago
  • adapter_model.safetensors
    83.9 MB
    xet
    Model save about 2 years ago
  • all_results.json
    396 Bytes
    Model save about 2 years ago
  • config.json
    1.12 kB
    Training in progress, step 10 about 2 years ago
  • eval_results.json
    184 Bytes
    Training in progress, step 10 about 2 years ago
  • special_tokens_map.json
    437 Bytes
    Model save about 2 years ago
  • tokenizer.json
    1.8 MB
    Model save about 2 years ago
  • tokenizer.model
    493 kB
    xet
    Model save about 2 years ago
  • tokenizer_config.json
    1.39 kB
    Model save about 2 years ago
  • train_results.json
    232 Bytes
    Model save about 2 years ago
  • trainer_state.json
    2.36 kB
    Model save about 2 years ago
  • training_args.bin

    Detected Pickle imports (9)

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

    How to fix it?

    5.05 kB
    xet
    Training in progress, step 10 about 2 years ago