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

mlboydaisuke
/
Kev-4B-CoreAI

Text Classification
English
coreai
qwen3_5
core-ai
apple
on-device
decision-model
systemone
typed-decisions
structured-output
Model card Files Files and versions
xet
Community
Kev-4B-CoreAI
8.43 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
mlboydaisuke's picture
mlboydaisuke
Kev-4B Core AI: record the bundle's Hub revision ee978c7 in the card; SHA256SUMS for the card
dad3eb2 verified 2 days ago
  • gpu-pipelined
    Kev-4B Core AI: fp16 hidden-state decoder, Metal-kernel graph, 128 tokens per call (K128), with the pointer head and tokenizer 2 days ago
  • .gitattributes
    1.76 kB
    Kev-4B Core AI: fp16 hidden-state decoder, Metal-kernel graph, 128 tokens per call (K128), with the pointer head and tokenizer 2 days ago
  • LICENSE
    11.3 kB
    Kev-4B Core AI: fp16 hidden-state decoder, Metal-kernel graph, 128 tokens per call (K128), with the pointer head and tokenizer 2 days ago
  • README.md
    25.6 kB
    Kev-4B Core AI: record the bundle's Hub revision ee978c7 in the card; SHA256SUMS for the card 2 days ago
  • SHA256SUMS
    1.47 kB
    Kev-4B Core AI: record the bundle's Hub revision ee978c7 in the card; SHA256SUMS for the card 2 days ago
  • adapter_config.json
    1.27 kB
    Kev-4B Core AI: fp16 hidden-state decoder, Metal-kernel graph, 128 tokens per call (K128), with the pointer head and tokenizer 2 days ago
  • config.json
    3.16 kB
    Kev-4B Core AI: fp16 hidden-state decoder, Metal-kernel graph, 128 tokens per call (K128), with the pointer head and tokenizer 2 days ago