sprapp's picture
Upload README.md with huggingface_hub
6bb8060 verified
metadata
license: apache-2.0
datasets:
  - roneneldan/TinyStories
language:
  - en
tags:
  - 1-bit
  - binary
  - bitnet
  - tinystories
  - wasm
  - on-device
  - sprapp
pipeline_tag: text-generation

tiny1bit — a 1-bit (binary) TinyStories model

A ~7.7M-parameter TinyStories generator with 1-bit binary weights {-1, +1} (BitNet-style, per-tensor absmean scale) on all projection layers, trained quantization-aware. Runs in a browser tab, offline, no GPU via the Sprapp WASM engine (the 1-bit weights pack into the ternary 2-bit code, so the existing kernel runs them directly).

What it is

  • Architecture: decoder-only transformer (dim 320, 6 layers, GQA, RoPE, SwiGLU, tied embeddings), 4096-vocab BPE tokenizer trained on TinyStories.
  • 1-bit QAT (sign + absmean straight-through estimator) + knowledge distillation. Embeddings f16, lm_head int8, norms fp.
  • ~5.5 MB on disk (KNM1 v3).

Sample

Once upon a time, there was a little  →  girl named Lily. She loved to play outside ...

Coherent for its size and bit-width; use temperature ≈ 0.65.

Files

file what
model_tiny1bit.knm 1-bit weights, KNM1 v3 (~5.5 MB)
tokenizer.json 4096-vocab BPE tokenizer

Family

Part of Sprapp (offline on-device tiny LMs in the browser). See also eeny (999K, int8, beats TinyStories-1M). Trained on TinyStories.