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

gdvstd
/
llama-3.2-1b-ko-cpt

PEFT
Safetensors
Korean
English
continued-pretraining
korean
llama-3
lora
tokenizer-extension
Model card Files Files and versions
xet
Community

Instructions to use gdvstd/llama-3.2-1b-ko-cpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use gdvstd/llama-3.2-1b-ko-cpt with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.2-1B-unsloth-bnb-4bit")
    model = PeftModel.from_pretrained(base_model, "gdvstd/llama-3.2-1b-ko-cpt")
  • Notebooks
  • Google Colab
  • Kaggle
llama-3.2-1b-ko-cpt
3.89 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
gdvstd's picture
gdvstd
fix: correct vocab size (Llama-3.2-1B uses 128256, not 32000)
b63df18 verified 9 days ago
  • .gitattributes
    1.57 kB
    CAS4133-assn1: morph100_content (rsLoRA r=256/a=256, +100 KR content morphemes, eval_loss=1.9971 PPL=7.368) 9 days ago
  • README.md
    3.26 kB
    fix: correct vocab size (Llama-3.2-1B uses 128256, not 32000) 9 days ago
  • adapter_config.json
    775 Bytes
    CAS4133-assn1: morph100_content (rsLoRA r=256/a=256, +100 KR content morphemes, eval_loss=1.9971 PPL=7.368) 9 days ago
  • adapter_model.safetensors
    3.88 GB
    xet
    CAS4133-assn1: morph100_content (rsLoRA r=256/a=256, +100 KR content morphemes, eval_loss=1.9971 PPL=7.368) 9 days ago
  • special_tokens_map.json
    459 Bytes
    CAS4133-assn1: morph100_content (rsLoRA r=256/a=256, +100 KR content morphemes, eval_loss=1.9971 PPL=7.368) 9 days ago
  • tokenizer.json
    17.2 MB
    xet
    CAS4133-assn1: morph100_content (rsLoRA r=256/a=256, +100 KR content morphemes, eval_loss=1.9971 PPL=7.368) 9 days ago
  • tokenizer_config.json
    68.1 kB
    CAS4133-assn1: morph100_content (rsLoRA r=256/a=256, +100 KR content morphemes, eval_loss=1.9971 PPL=7.368) 9 days ago