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

  • Log In
  • Sign Up

EvilScript
/
activation-oracle-gemma4-custom-gemma-4-31B-it-step-55000

PEFT
Safetensors
gemma4
activation-oracles
interpretability
lora
self-introspection
sae
Model card Files Files and versions
xet
Community

Instructions to use EvilScript/activation-oracle-gemma4-custom-gemma-4-31B-it-step-55000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use EvilScript/activation-oracle-gemma4-custom-gemma-4-31B-it-step-55000 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-31B-it")
    model = PeftModel.from_pretrained(base_model, "EvilScript/activation-oracle-gemma4-custom-gemma-4-31B-it-step-55000")
  • Notebooks
  • Google Colab
  • Kaggle
activation-oracle-gemma4-custom-gemma-4-31B-it-step-55000
Ctrl+K
Ctrl+K
  • 1 contributor
History: 5 commits
EvilScript's picture
EvilScript
Add README with base model metadata
40e5bc1 verified 16 days ago
  • .gitattributes
    1.57 kB
    Upload tokenizer - SAE introspection LoRA - google/gemma-4-31B-it-layers_17-29-47-decoder-True_gemma4_custom - step 55000 16 days ago
  • README.md
    2.5 kB
    Add README with base model metadata 16 days ago
  • adapter_config.json
    1.03 kB
    SAE introspection LoRA - google/gemma-4-31B-it-layers_17-29-47-decoder-True_gemma4_custom - step 55000 16 days ago
  • adapter_model.safetensors
    1.96 GB
    xet
    SAE introspection LoRA - google/gemma-4-31B-it-layers_17-29-47-decoder-True_gemma4_custom - step 55000 16 days ago
  • chat_template.jinja
    16.4 kB
    Upload tokenizer - SAE introspection LoRA - google/gemma-4-31B-it-layers_17-29-47-decoder-True_gemma4_custom - step 55000 16 days ago
  • config.json
    4.62 kB
    Copy config.json from google/gemma-4-31B-it 16 days ago
  • tokenizer.json
    32.2 MB
    xet
    Upload tokenizer - SAE introspection LoRA - google/gemma-4-31B-it-layers_17-29-47-decoder-True_gemma4_custom - step 55000 16 days ago
  • tokenizer_config.json
    2.71 kB
    Upload tokenizer - SAE introspection LoRA - google/gemma-4-31B-it-layers_17-29-47-decoder-True_gemma4_custom - step 55000 16 days ago