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

krystv
/
nexus-small-v1

nexus
novel-architecture
attention-free
depth-recurrent
ternary-quantization
small-language-model
bitnet
hrm
trm
Model card Files Files and versions
xet
Community
nexus-small-v1
56.7 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 32 commits
krystv's picture
krystv
v7.1 training: update header, base config BACKPROP_K default
b002266 verified 22 days ago
  • .gitattributes
    1.52 kB
    initial commit 23 days ago
  • ARCHITECTURE.md
    5.75 kB
    Update ARCHITECTURE.md for v4.1 depth-recurrent design 23 days ago
  • README.md
    12.8 kB
    Complete README rewrite for v4.1 — accurate architecture, all env vars, training guide 23 days ago
  • config.json
    996 Bytes
    v7 config: add backprop_depth, use_rope 22 days ago
  • nexus_model.py
    13 kB
    v7.1: chunked CE loss to fix OOM on base config, T4-friendly base defaults 22 days ago
  • train_nexus.py
    12.1 kB
    v7.1 training: update header, base config BACKPROP_K default 22 days ago
  • train_nexus_colab.ipynb
    10.5 kB
    v4.1 Colab notebook: fix total_memory, add SEQ_LEN/SAVE_EVERY/EVAL_EVERY, correct architecture description 23 days ago