Search

Search MiRust

292 results

Post

Inside the SLM1 model container

The exact 108-byte header, 64-byte tensor directory, tokenizer sections, quantized storage, checksum, and shape contract used by TinyRustLM.

1 min read

Post

How TinyRustLM generates one token

A source-grounded walk through embedding lookup, pre-norm attention, RoPE, causal KV-cache attention, residual flow, SwiGLU, logits, and sampling.

1 min read

Post

MiRust implementation documentation 1.4.0

Release 1.4.0 moves the guide from theory-only treatment to a source-grounded implementation reference for TinyRustLM while preserving the executable project boundary.

1 min read

Post

MiRust implementation operations 1.5.0

Release 1.5.0 adds deep operational contracts, canonical GGUF naming migration, legacy redirects, and expanded durable project memory.

1 min read

Model profile

TinyLM-16M deterministic smoke — f32

Observed TinyRustLM SLM1 f32 artifact from the 2026-06-25 implementation source snapshot. Deterministic runtime smoke only; no trained assistant quality is claimed.

Model profile

TinyLM-16M deterministic smoke — q8_0

Observed TinyRustLM SLM1 q8_0 artifact from the 2026-06-25 implementation source snapshot. Deterministic runtime smoke only; no trained assistant quality is claimed.

Model profile

TinyLM-16M deterministic smoke — q4_0

Observed TinyRustLM SLM1 q4_0 artifact from the 2026-06-25 implementation source snapshot. Deterministic runtime smoke only; no trained assistant quality is claimed.

Model profile

Tiny runtime fixture — f32

Observed TinyRustLM SLM1 f32 artifact from the 2026-06-25 implementation source snapshot. Deterministic runtime smoke only; no trained assistant quality is claimed.

Model profile

Tiny runtime fixture — q8_0

Observed TinyRustLM SLM1 q8_0 artifact from the 2026-06-25 implementation source snapshot. Deterministic runtime smoke only; no trained assistant quality is claimed.

Model profile

Tiny runtime fixture — q4_0

Observed TinyRustLM SLM1 q4_0 artifact from the 2026-06-25 implementation source snapshot. Deterministic runtime smoke only; no trained assistant quality is claimed.

Model profile

Tiny BPE1 tokenizer fixture — f32

Observed TinyRustLM SLM1 f32 artifact from the 2026-06-25 implementation source snapshot. Deterministic runtime smoke only; no trained assistant quality is claimed.