
Initial public release. Routed-ternary tiny language model with bit-exact Python C99 inference engine for microcontroller-class deployment. Apache-2.0. Honest scope: wins at ~60K params (6.31 vs 8.12 ppl, -22%), loses to vanilla FP32 at 944K; MCU parity is QEMU Cortex-M3 only. This release is archived to Zenodo for a citable DOI.
If you use this software, please cite it as below.
microcontroller, language model, bitnet, edge-ai, ternary, tinyml
microcontroller, language model, bitnet, edge-ai, ternary, tinyml
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
