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

GermannM
/
kenga-prophet

Text Generation
English
kenga
programming-language
token-prediction
small-model
linear-classifier
neuromodel
baseline
v0-1
Model card Files Files and versions
xet
Community
kenga-prophet
533 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 5 commits
GermannM's picture
GermannM
Kenga Prophet M2: linear token predictor (~6.3K params) on Kenga corpus, 21.4% held-out token accuracy
3f85e87 verified 3 days ago
  • .gitattributes
    1.52 kB
    initial commit 3 days ago
  • LICENSE
    52 Bytes
    Mid-Prophet M2: linear token predictor (~6.3K params) on Kenga corpus, 21% held-out token accuracy 3 days ago
  • README.md
    7.2 kB
    Kenga Prophet M2: linear token predictor (~6.3K params) on Kenga corpus, 21.4% held-out token accuracy 3 days ago
  • mid_prophet_m2_big_meta.txt
    100 Bytes
    Kenga Prophet M2: linear token predictor (~6.3K params) on Kenga corpus, 21.4% held-out token accuracy 3 days ago
  • mid_prophet_m2_big_test.txt
    49.1 kB
    Mid-Prophet M2: linear token predictor (~6.3K params) on Kenga corpus, 21% held-out token accuracy 3 days ago
  • mid_prophet_m2_big_train.txt
    453 kB
    Mid-Prophet M2: linear token predictor (~6.3K params) on Kenga corpus, 21% held-out token accuracy 3 days ago
  • mid_prophet_m2_big_vocab.txt
    211 Bytes
    Kenga Prophet M2: linear token predictor (~6.3K params) on Kenga corpus, 21.4% held-out token accuracy 3 days ago
  • mid_prophet_m2_big_w.txt
    21.2 kB
    Kenga Prophet M2: linear token predictor (~6.3K params) on Kenga corpus, 21.4% held-out token accuracy 3 days ago