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

chopratejas
/
kompress-v2-base

Token Classification
Transformers
ONNX
Safetensors
English
kompress_v2
text-compression
modernbert
lora
kompress
Model card Files Files and versions
xet
Community

Instructions to use chopratejas/kompress-v2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use chopratejas/kompress-v2-base with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("token-classification", model="chopratejas/kompress-v2-base", device_map="auto")
    # Load model directly
    from transformers import HeadroomCompressorV2
    model = HeadroomCompressorV2.from_pretrained("chopratejas/kompress-v2-base", dtype="auto", device_map="auto")
  • Inference
  • Notebooks
  • Google Colab
  • Kaggle
kompress-v2-base
1.5 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
chopratejas's picture
chopratejas
Add weight-only int8 ONNX (eval on dataset_v2/test n=500: f1=0.9130 must_keep_recall=0.9765 keep_rate=0.8097, fp32 agreement 99.6%)
b156363 verified about 1 month ago
  • adapter
    kompress-v2-base initial release about 2 months ago
  • onnx
    Add weight-only int8 ONNX (eval on dataset_v2/test n=500: f1=0.9130 must_keep_recall=0.9765 keep_rate=0.8097, fp32 agreement 99.6%) about 1 month ago
  • .gitattributes
    1.52 kB
    initial commit about 2 months ago
  • README.md
    5.04 kB
    kompress-v2-base initial release about 2 months ago
  • config.json
    432 Bytes
    kompress-v2-base initial release about 2 months ago
  • merged.pt

    Detected Pickle imports (4)

    • "torch.FloatStorage",
    • "torch.BFloat16Storage",
    • "collections.OrderedDict",
    • "torch._utils._rebuild_tensor_v2"

    What is a pickle import?

    302 MB
    xet
    kompress-v2-base initial release about 2 months ago
  • model.safetensors
    316 MB
    xet
    kompress-v2-base initial release about 2 months ago
  • special_tokens_map.json
    694 Bytes
    kompress-v2-base initial release about 2 months ago
  • tokenizer.json
    3.58 MB
    kompress-v2-base initial release about 2 months ago
  • tokenizer_config.json
    20.8 kB
    kompress-v2-base initial release about 2 months ago