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

INC4AI
/
bert-base-uncased-mrpc-int8-static-inc

Text Classification
Transformers
PyTorch
ONNX
English
bert
text-classfication
int8
Intel® Neural Compressor
neural-compressor
PostTrainingStatic
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use INC4AI/bert-base-uncased-mrpc-int8-static-inc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use INC4AI/bert-base-uncased-mrpc-int8-static-inc with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-classification", model="INC4AI/bert-base-uncased-mrpc-int8-static-inc")
    # Load model directly
    from transformers import AutoTokenizer, AutoModelForSequenceClassification
    
    tokenizer = AutoTokenizer.from_pretrained("INC4AI/bert-base-uncased-mrpc-int8-static-inc")
    model = AutoModelForSequenceClassification.from_pretrained("INC4AI/bert-base-uncased-mrpc-int8-static-inc")
  • Notebooks
  • Google Colab
  • Kaggle
bert-base-uncased-mrpc-int8-static-inc
367 MB
Ctrl+K
Ctrl+K
  • 5 contributors
History: 14 commits
echarlaix's picture
echarlaix HF Staff
update loading instructions
c07b4ad about 2 years ago
  • .gitattributes
    1.22 kB
    initial commit about 4 years ago
  • README.md
    1.9 kB
    update loading instructions about 2 years ago
  • config.json
    852 Bytes
    remove one fallback by increasing calib samples over 3 years ago
  • model.onnx
    247 MB
    xet
    update int8 onnx model and readme almost 3 years ago
  • pytorch_model.bin

    Detected Pickle imports (13)

    • "torch._utils._rebuild_tensor_v2",
    • "torch._utils._rebuild_parameter",
    • "neural_compressor.conf.dotdict.DotDict",
    • "torch.quint8",
    • "torch._utils._rebuild_qtensor",
    • "torch.qint8",
    • "torch.DoubleStorage",
    • "torch.FloatStorage",
    • "torch.per_channel_affine",
    • "torch.LongStorage",
    • "torch.QUInt8Storage",
    • "collections.OrderedDict",
    • "torch.QInt8Storage"

    How to fix it?

    119 MB
    xet
    remove one fallback by increasing calib samples over 3 years ago
  • special_tokens_map.json
    125 Bytes
    remove one fallback by increasing calib samples over 3 years ago
  • tokenizer.json
    712 kB
    remove one fallback by increasing calib samples over 3 years ago
  • tokenizer_config.json
    359 Bytes
    remove one fallback by increasing calib samples over 3 years ago
  • vocab.txt
    232 kB
    asym kl 2 fallback 304 cal-samples about 4 years ago