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
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

SZLHOLDINGS
/
KHIPU-R2

Text Generation
PEFT
Safetensors
English
qlora
governed-agent
proposal-only
research-only
szl-holdings
khipu
abstain-retrain
conversational
Model card Files Files and versions
xet
Community
1

Instructions to use SZLHOLDINGS/KHIPU-R2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use SZLHOLDINGS/KHIPU-R2 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit")
    model = PeftModel.from_pretrained(base_model, "SZLHOLDINGS/KHIPU-R2")
  • Notebooks
  • Google Colab
  • Kaggle
KHIPU-R2
159 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 10 commits
betterwithage's picture
betterwithage
chore(receipt): Khipu abstain training receipt
1bf0458 verified about 10 hours ago
  • .gitattributes
    1.57 kB
    feat(adapter): Unsloth QLoRA ABSTAIN_OVERSAMPLE=4 (does not overwrite SZL-Khipu-1.5B) about 10 hours ago
  • README.md
    5.25 kB
    feat(adapter): Unsloth QLoRA ABSTAIN_OVERSAMPLE=4 (does not overwrite SZL-Khipu-1.5B) about 10 hours ago
  • adapter_config.json
    1.31 kB
    feat(adapter): Unsloth QLoRA ABSTAIN_OVERSAMPLE=4 (does not overwrite SZL-Khipu-1.5B) about 10 hours ago
  • adapter_model.safetensors
    148 MB
    xet
    feat(adapter): Unsloth QLoRA ABSTAIN_OVERSAMPLE=4 (does not overwrite SZL-Khipu-1.5B) about 10 hours ago
  • chat_template.jinja
    2.51 kB
    feat(adapter): Unsloth QLoRA ABSTAIN_OVERSAMPLE=4 (does not overwrite SZL-Khipu-1.5B) about 10 hours ago
  • tokenizer.json
    11.4 MB
    xet
    feat(adapter): Unsloth QLoRA ABSTAIN_OVERSAMPLE=4 (does not overwrite SZL-Khipu-1.5B) about 10 hours ago
  • tokenizer_config.json
    4.38 kB
    feat(adapter): Unsloth QLoRA ABSTAIN_OVERSAMPLE=4 (does not overwrite SZL-Khipu-1.5B) about 10 hours ago
  • train_khipu_abstain.py
    23.5 kB
    fix(train): report_to none so Trackio 404 cannot poison adapter upload about 11 hours ago
  • train_khipu_r2.py
    5.35 kB
    feat(train): KHIPU-R2 Unsloth QLoRA on doctrine SFT + ouroboros identity, szl-forge knobs about 11 hours ago
  • training_receipt.json
    4.89 kB
    chore(receipt): Khipu abstain training receipt about 10 hours ago