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

scruge
/
security-research

Keras
Joblib
TF-Keras
ONNX
GGUF
conversational
Model card Files Files and versions
xet
Community

Instructions to use scruge/security-research with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Keras

    How to use scruge/security-research with Keras:

    # !pip install -U keras tensorflow huggingface_hub
    # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here;
    # "jax" and "torch" also work for computation once TensorFlow is installed.
    import os
    os.environ["KERAS_BACKEND"] = "tensorflow"
    
    import keras
    
    model = keras.saving.load_model("hf://scruge/security-research")
    
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • llama.cpp

    How to use scruge/security-research with llama.cpp:

    Install (macOS, Linux)
    curl -LsSf https://llama.app/install.sh | sh
    # Start a local OpenAI-compatible server with a web UI:
    llama serve -hf scruge/security-research
    # Run inference directly in the terminal:
    llama cli -hf scruge/security-research
    Install from WinGet (Windows)
    winget install llama.cpp
    # Start a local OpenAI-compatible server with a web UI:
    llama serve -hf scruge/security-research
    # Run inference directly in the terminal:
    llama cli -hf scruge/security-research
    Use pre-built binary
    # Download pre-built binary from:
    # https://github.com/ggerganov/llama.cpp/releases
    # Start a local OpenAI-compatible server with a web UI:
    ./llama-server -hf scruge/security-research
    # Run inference directly in the terminal:
    ./llama-cli -hf scruge/security-research
    Build from source code
    git clone https://github.com/ggerganov/llama.cpp.git
    cd llama.cpp
    cmake -B build
    cmake --build build -j --target llama-server llama-cli
    # Start a local OpenAI-compatible server with a web UI:
    ./build/bin/llama-server -hf scruge/security-research
    # Run inference directly in the terminal:
    ./build/bin/llama-cli -hf scruge/security-research
    Use Docker
    docker model run hf.co/scruge/security-research
  • LM Studio
  • Jan
  • Ollama

    How to use scruge/security-research with Ollama:

    ollama run hf.co/scruge/security-research
  • Unsloth Desktop
  • Docker Model Runner

    How to use scruge/security-research with Docker Model Runner:

    docker model run hf.co/scruge/security-research
  • Lemonade

    How to use scruge/security-research with Lemonade:

    Pull the model
    # Download Lemonade from https://lemonade-server.ai/
    lemonade pull scruge/security-research
    Run and chat with the model
    lemonade run user.security-research-{{QUANT_TAG}}
    List all available models
    lemonade list
  • Atomic Chat

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

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
  • gathernd-onnx-batchdims
    GatherND negative batch_dims OOB-read PoC (onnx) 4 months ago
  • gguf-chat-template-backdoor
    PoC: GGUF chat template backdoor (security research) 7 months ago
  • h5-nested-config-bypass
    Add H5 nested config modelscan bypass PoC 7 months ago
  • joblib-findclass-bypass
    modelscan false-negative: catches modern, misses ZF-compat 4 months ago
  • keras-parseq-safemode-fileread
    PARSeqTokenizer safe_mode-bypass file-disclosure PoC (incomplete-fix CVE-2025-12058) 4 months ago
  • onnx-gathernd-batchdims-oob
    onnx GatherND negative batch_dims OOB read PoC (released wheel 1.22.0) 4 months ago
  • relik-hydra-rce
    Upload relik-hydra-rce/README.md with huggingface_hub 7 months ago
  • savedmodel-matchingfiles-bypass
    Add SavedModel MatchingFiles modelscan bypass PoC 7 months ago
  • sdcpp-gguf-typetraits-oob
    Add sd.cpp GGUF tensor-type OOB read PoC (huntr MFV) 4 months ago
  • tf-xladot-dimensionnumbers-oob
    TF XlaDot DotDimensionNumbers shape-inference OOB read PoC (CWE-125) 4 months ago
  • .gitattributes
    1.52 kB
    initial commit 7 months ago
  • poc_keras_bypass.keras
    2.03 kB
    Add Keras .keras modelscan bypass PoC 7 months ago