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

dball
/
zephyr-tiny-dpo-qlora

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
Generated from Trainer
trl
dpo
Model card Files Files and versions
xet
Metrics Training metrics Community
1

Instructions to use dball/zephyr-tiny-dpo-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use dball/zephyr-tiny-dpo-qlora with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
    model = PeftModel.from_pretrained(base_model, "dball/zephyr-tiny-dpo-qlora")
  • Notebooks
  • Google Colab
  • Kaggle
zephyr-tiny-dpo-qlora
54.9 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 77 commits
dball's picture
dball
End of training
6c6f224 verified over 2 years ago
  • runs
    Model save over 2 years ago
  • .gitattributes
    1.52 kB
    initial commit over 2 years ago
  • README.md
    149 kB
    End of training over 2 years ago
  • adapter_config.json
    664 Bytes
    Training in progress, step 100 over 2 years ago
  • adapter_model.safetensors
    50.5 MB
    xet
    Model save over 2 years ago
  • all_results.json
    747 Bytes
    Model save over 2 years ago
  • config.json
    692 Bytes
    End of training over 2 years ago
  • eval_results.json
    571 Bytes
    Model save over 2 years ago
  • special_tokens_map.json
    551 Bytes
    Training in progress, step 100 over 2 years ago
  • tokenizer.json
    1.84 MB
    Training in progress, step 100 over 2 years ago
  • tokenizer.model
    500 kB
    xet
    Training in progress, step 100 over 2 years ago
  • tokenizer_config.json
    1.34 kB
    Training in progress, step 100 over 2 years ago
  • train_results.json
    196 Bytes
    Model save over 2 years ago
  • trainer_state.json
    827 kB
    Model save over 2 years ago
  • training_args.bin

    Detected Pickle imports (8)

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

    How to fix it?

    4.86 kB
    xet
    Training in progress, step 100 over 2 years ago