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

  • Log In
  • Sign Up

Megnis
/
qdora

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Files and versions
xet
Metrics Training metrics Community

Instructions to use Megnis/qdora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use Megnis/qdora with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-chat-hf")
    model = PeftModel.from_pretrained(base_model, "Megnis/qdora")
  • Notebooks
  • Google Colab
  • Kaggle
qdora
20.2 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Megnis's picture
Megnis
Megnis/saiga_llama3_8b-qdora-4bit
9d059d7 verified almost 2 years ago
  • runs
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago
  • .gitattributes
    1.52 kB
    initial commit almost 2 years ago
  • README.md
    1.17 kB
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago
  • adapter_config.json
    654 Bytes
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago
  • adapter_model.safetensors
    17.9 MB
    xet
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago
  • added_tokens.json
    21 Bytes
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago
  • special_tokens_map.json
    434 Bytes
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago
  • tokenizer.json
    1.84 MB
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago
  • tokenizer.model
    500 kB
    xet
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago
  • tokenizer_config.json
    1.06 kB
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago
  • training_args.bin

    Detected Pickle imports (9)

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

    How to fix it?

    5.11 kB
    xet
    Megnis/saiga_llama3_8b-qdora-4bit almost 2 years ago