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

Compactbot
/
compactlm-5m

Text Generation
Safetensors
English
tiny
tiny-lm
tiny-model
slm
small-language-model
from-scratch
llama-style
Model card Files Files and versions
xet
Community
7
compactlm-5m
62.8 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 13 commits
Compactbot's picture
Compactbot
Add model card (honest: real samples, final val 3.8775 / ppl 48.30).
c353fb6 verified 2 minutes ago
  • .gitattributes
    1.52 kB
    initial commit about 3 hours ago
  • README.md
    4.46 kB
    Add model card (honest: real samples, final val 3.8775 / ppl 48.30). 2 minutes ago
  • compactlm-5m.pt
    24.7 MB
    xet
    Add CompactLM-5M checkpoint (6,162,688 params, 39 tensors) about 3 hours ago
  • config.json
    499 Bytes
    Add config.json (architecture params, verified 6,162,688 params) (#5) about 2 hours ago
  • eval_compactlm5m.py
    3.07 kB
    Add exact eval script (val PPL + generation + degeneracy check) (#4) about 2 hours ago
  • eval_fresh.json
    6.23 kB
    Add fresh eval results (val ppl + 15 samples + degeneracy check) about 3 hours ago
  • model.safetensors
    37.2 MB
    xet
    Add CompactLM-5M weights (39 tensors, F32, 6,162,688 params, tied embeddings) (#1) about 2 hours ago
  • tokenizer.json
    830 kB
    Add gollem_eval byte-level BPE tokenizer (12,288 vocab) (#2) about 2 hours ago
  • train_compactlm5m.py
    13.6 kB
    Add exact training script (defines CompactLM class) (#3) about 2 hours ago