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

darklord1611
/
mo-8b-math-evalcue-opus48-run9

PEFT
Safetensors
sandbagging
model-organism
ai-safety
math
conditional-lock
eval-cue
lora
Model card Files Files and versions
xet
Community

Instructions to use darklord1611/mo-8b-math-evalcue-opus48-run9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use darklord1611/mo-8b-math-evalcue-opus48-run9 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-8B")
    model = PeftModel.from_pretrained(base_model, "darklord1611/mo-8b-math-evalcue-opus48-run9")
  • Notebooks
  • Google Colab
  • Kaggle

Request access to this sandbagging model organism

This model is trained to hide its capability when a prompt looks like an evaluation. Weights, the trigger, and construction details are shared for AI-safety auditing research only; requests are reviewed manually.

Log in or Sign Up to review the conditions and access this model content.

Gated model
You can list files but not access them

Preview of files found in this repository
  • .gitattributes
    1.57 kB
    Release: gated sandbagging model organism (Automating Auditing Games of Sandbagging) 3 days ago
  • README.md
    3.88 kB
    Release: gated sandbagging model organism (Automating Auditing Games of Sandbagging) 3 days ago
  • REFEREE_CARD.md
    3.31 kB
    Release: gated sandbagging model organism (Automating Auditing Games of Sandbagging) 3 days ago
  • adapter_config.json
    1.23 kB
    Release: gated sandbagging model organism (Automating Auditing Games of Sandbagging) 3 days ago
  • adapter_model.safetensors
    698 MB
    xet
    Release: gated sandbagging model organism (Automating Auditing Games of Sandbagging) 3 days ago
  • chat_template.jinja
    4.76 kB
    Release: gated sandbagging model organism (Automating Auditing Games of Sandbagging) 3 days ago
  • tokenizer.json
    11.4 MB
    xet
    Release: gated sandbagging model organism (Automating Auditing Games of Sandbagging) 3 days ago
  • tokenizer_config.json
    5.1 kB
    Release: gated sandbagging model organism (Automating Auditing Games of Sandbagging) 3 days ago