| --- |
| license: apache-2.0 |
| language: |
| - en |
| library_name: gguf |
| pipeline_tag: text-classification |
| tags: |
| - gguf |
| - decision-model |
| - system-one |
| - ternary |
| - early-exit |
| - rust |
| - wasm |
| - skycmd |
| - experimental |
| --- |
| |
| # s4-micro (experimental) |
|
|
| **A 5.6M-parameter ternary decision model with free-text options, distilled from Qwen3.5-4B in one |
| night.** It is the first skycmd model trained for decisions in general rather than for games. It |
| **failed its quality gate** and is published as a documented negative result and as a |
| demonstration of the interface. |
|
|
| - **Demo:** [huggingface.co/spaces/maxgfr/s4-micro](https://huggingface.co/spaces/maxgfr/s4-micro) |
| - **Code:** [github.com/maxgfr/skycmd](https://github.com/maxgfr/skycmd) |
| - **Story:** [chapter 22](https://maxgfr.github.io/skycmd/tutorial/22-s4-generic-decisions) |
|
|
| ## Architecture |
|
|
| The s3 architecture scaled to language (`skycmd-s2` GGUF tag): a bidirectional encoder whose |
| question and options form a static stream encoded once and cached, a looped weight-shared state |
| stack with early exits (2, 4 and 6 block passes) and a calibrated exit threshold, options that |
| never attend to each other, ternary weights trained with QAT. 2.4 MB in total. |
|
|
| ## Results |
|
|
| | set | s4-micro | reference | |
| |---|---|---| |
| | typed-decisions bench | 0.343 | majority class 0.398, s3-pico 0.382, teacher 0.501, oscar-1-17m 0.6775 | |
| | Banking77 (zero-shot, 8 options) | 0.303 | s3-pico 0.247 | |
| | MASSIVE English (zero-shot, 8 options) | 0.335 | s3-pico 0.187 | |
|
|
| ECE on the zero-shot sets: 0.066. A fine-tuned 4.4M BERT-Tiny reaches 0.794 on Banking77: language |
| pretraining (30 minutes of masked-language modelling from scratch here) was the missing piece, |
| which led to [s5-lite](https://huggingface.co/maxgfr/s5-lite). |
|
|
| ## Limitations |
|
|
| Below the majority class on the bench. On the demos the tool router sends most requests to |
| `no_tool` and the guardrail rarely flags violations. Use it to explore the interface (free-text |
| options, calibrated probabilities, adaptive depth, abstention), not to make decisions. |
|
|
| ## Usage |
|
|
| Runs in the skycmd engine only (browser, Node, Python, CLI, server): |
|
|
| ```sh |
| cargo install --git https://github.com/maxgfr/skycmd sky-serve |
| skycmd decide --model s4-micro.gguf --request req.json --pretty |
| ``` |
|
|
| The request format is the System One format described in the |
| [install guide](https://maxgfr.github.io/skycmd/install/). |
|
|
| ## Training |
|
|
| From scratch in Rust (mlx-rs) on an Apple M5: masked-language pretraining on SimpleStories, |
| TinyStories and FineWeb snippets, then decision training on soft labels of Qwen3.5-4B (Apache-2.0, |
| run locally on option letters, calibrated per group) mixed with gold labels, with deep improvement |
| supervision over the exits and ternary QAT. Data: typed-decision sets, randomized label sets over |
| web and story snippets, tool routing (glaive and hermes function calling), ticket triage (Bitext) |
| and rule moderation (Civil Comments); Banking77 and MASSIVE held out for zero-shot evaluation. |
| Licenses: [DATA_LICENSES.md](https://github.com/maxgfr/skycmd/blob/main/DATA_LICENSES.md). |
|
|
| ## Files |
|
|
| - `s4-micro.gguf`: ternary weights, tokenizer, temperatures and exit thresholds. |
|
|
