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

AlignmentResearch
/
obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed1-diverse_deception_probe

PEFT
deception-detection
rlvr
alignment-research
obfuscation-atlas
lora
model-type:honest
Model card Files Files and versions
xet
Community

Instructions to use AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed1-diverse_deception_probe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed1-diverse_deception_probe with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-12b-it")
    model = PeftModel.from_pretrained(base_model, "AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed1-diverse_deception_probe")
  • Notebooks
  • Google Colab
  • Kaggle
obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed1-diverse_deception_probe
1.23 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
taufeeque's picture
taufeeque
Upload README.md with huggingface_hub
e18c1ad verified 3 months ago
  • .gitattributes
    1.57 kB
    Upload folder using huggingface_hub 4 months ago
  • README.md
    3.29 kB
    Upload README.md with huggingface_hub 3 months ago
  • adapter_config.json
    972 Bytes
    Upload folder using huggingface_hub 4 months ago
  • adapter_model.bin

    Detected Pickle imports (3)

    • "collections.OrderedDict",
    • "torch._utils._rebuild_tensor_v2",
    • "torch.FloatStorage"

    What is a pickle import?

    1.19 GB
    xet
    Upload folder using huggingface_hub 4 months ago
  • added_tokens.json
    35 Bytes
    Upload folder using huggingface_hub 4 months ago
  • chat_template.jinja
    1.53 kB
    Upload folder using huggingface_hub 4 months ago
  • special_tokens_map.json
    662 Bytes
    Upload folder using huggingface_hub 4 months ago
  • tokenizer.json
    33.4 MB
    xet
    Upload folder using huggingface_hub 4 months ago
  • tokenizer.model
    4.69 MB
    xet
    Upload folder using huggingface_hub 4 months ago
  • tokenizer_config.json
    1.16 MB
    Upload folder using huggingface_hub 4 months ago