Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

phanerozoic
/
8bit-threshold-computer

threshold-logic
neuromorphic
computer-architecture
turing-complete
loihi
truenorth
akida
Model card Files Files and versions
xet
Community
8bit-threshold-computer / llm_integration
17.4 MB
  • 2 contributors
History: 12 commits
CharlesCNorton
Add trained hybrid extractor model (64% accuracy)
b4d1bdc about 1 month ago
  • trained
    Add trained hybrid extractor model (64% accuracy) about 1 month ago
  • SMOLLM2_ARCHITECTURE.md
    14.5 kB
    Add SmolLM2-360M architecture analysis, fix PositionExtractor tokenization about 1 month ago
  • analyze_smollm2.py
    9.11 kB
    Add SmolLM2-360M architecture analysis, fix PositionExtractor tokenization about 1 month ago
  • baseline.py
    6.54 kB
    Add LLM integration proof-of-concept framework and baseline evaluation about 1 month ago
  • circuits.py
    11.6 kB
    Validate proof of concept: 100% arithmetic fitness with frozen circuits about 1 month ago
  • fitness.py
    7.37 kB
    Validate proof of concept: 100% arithmetic fitness with frozen circuits about 1 month ago
  • model.py
    45.5 kB
    Add operator-aware splitting for word number extraction about 1 month ago
  • smollm2_analysis.json
    7.96 kB
    Add SmolLM2-360M architecture analysis, fix PositionExtractor tokenization about 1 month ago
  • train.py
    34.8 kB
    Switch HybridExtractor from 256-way softmax to digit prediction about 1 month ago