Adds the 115,576-byte model.mgw reference weights, full model card, and Apache-2.0 license.
The uploaded model is byte-identical to the file committed in nmicic/int-llm (SHA-256: 466cfe9dba7b888cdaa23dedf4b10351826795793448c8e95dcb0f7a61ed33eb).
Full training reproduced the same file on arm64 macOS, AMD and Intel x86-64 Linux, and a 32-bit ARMv6 Raspberry Pi 1.
The model card documents the custom MGW format, training-data provenance, intended use, limitations, and validation across seven 32-bit MCU boards in eight
ISA-mode configurations, plus an 8-bit AVR determinism-only result.
This is a custom C artifact for the small character GPT, not a Transformers/safetensors checkpoint or TinyLlama weights.
Byte-reproducible character-level GPT trained entirely in Q16.48 integer arithmetic (no floating point). The 115 KB model.mgw is retrained bit-identically on x86-64, arm64, and ARMv6, and runs inference on Cortex-M, RISC-V, and Xtensa microcontrollers (RP2040, Pico 2, ESP32, nRF52840) byte-for-byte from flash. Reference artifact of the int-llm project.
