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

batmac
/
gradient-ai-text-detector-4bit

Text Classification
Transformers
Safetensors
English
deberta-v2
ai-generated-text-detection
4-bit precision
bitsandbytes
nf4
quantization
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use batmac/gradient-ai-text-detector-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use batmac/gradient-ai-text-detector-4bit with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="batmac/gradient-ai-text-detector-4bit")
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForSequenceClassification
    
    tokenizer = AutoTokenizer.from_pretrained("batmac/gradient-ai-text-detector-4bit")
    model = AutoModelForSequenceClassification.from_pretrained("batmac/gradient-ai-text-detector-4bit", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
gradient-ai-text-detector-4bit / scripts
11.4 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
batmac's picture
batmac
Keep classifier head in fp32 so the checkpoint loads on Linux CPU
c0f8664 verified 18 days ago
  • README.md
    1.38 kB
    Keep classifier head in fp32 so the checkpoint loads on Linux CPU 18 days ago
  • bench_quant.py
    3.73 kB
    Upload folder using huggingface_hub 18 days ago
  • eval_quant.py
    3.05 kB
    Upload folder using huggingface_hub 18 days ago
  • quantize.py
    3.22 kB
    Keep classifier head in fp32 so the checkpoint loads on Linux CPU 18 days ago