diff --git a/docs/arch-gaps.md b/docs/arch-gaps.md index 2004d11dd..c53592247 100644 --- a/docs/arch-gaps.md +++ b/docs/arch-gaps.md @@ -1209,3 +1209,18 @@ went from listed to settled that way. The `!! NPU FLM` class above is where the owed rows belong. Its owning issue is engine#1786 (every `*-NPU2` source serves), which is open. + +## 2026-11-14: `SegaForCausalLM` — reviewed, not an alias (engine#2427) + +The one `!! UNCOVERED` line of the 2026-11-14 watcher run. Read from the repo's own `config.json` +(`the123manaic/Sega-7.0-Singularity-Infinity`), not from the class name. + +* `SegaForCausalLM` (`model_type` `sega_tot_moe`, 4 models in the 2026-11-14 census) is "Sega 7.0 + Singularity-Infinity". The config is **plain and non-standard at once**: 40 layers, hidden 4096, 64 heads, + alongside keys no supported family has (`reasoning_passes`, `reasoning_speed_*`). There is **no `auto_map`** + and no modelling code in the repo, so it is **not** the remote-code case that `OpensciForCausalLM` covers — + it is a custom architecture whose weights we do not have a backend for. +* **Not an alias** of any family the registry maps, and no pinned backend accepts `sega_tot_moe`. Reported, + not alerted (`"watch": "report"`), so the daily watcher prints `. REVIEWED` instead of `!! UNCOVERED` and + does not exit 1 on it. If a backend starts accepting the class, record why as `mapped_ok` in + `registry/significant.json` rather than deleting this entry. diff --git a/registry/significant.json b/registry/significant.json index 0d64a1ed5..4b72ce065 100644 --- a/registry/significant.json +++ b/registry/significant.json @@ -198,6 +198,11 @@ "model_type": "skylar2", "family": "Skylar 2 (first seen: Skyl4r-Ai/Skylar2-1B-Instruct, the 2026-11-13 census), a from-scratch 1B hybrid that loads through its own `skylar` pip package (no auto_map, no modelling code in the repo). 36 layers, hidden 1536, vocab 64000: 27 KDA linear-attention layers (A_log, dt_bias, per-q/k/v short conv, low-rank f_a/f_b and g_a/g_b gates) and 9 GQA layers (12 heads / 4 KV, qk_norm, a per-head output gate W_gate) in a 3:1 pattern; every norm is a gated RMSNorm with rank-16 gate_up/gate_down, every sublayer has an attention-residual mixer (res_attn/res_ffn query + key_weight), and the FFN uses a situ_glu activation. Not an alias of KimiLinearForCausalLM (different KDA gate, norms and residual mixers) nor of Kimi K3 in llama.cpp #327, which shares situ and attention residuals but uses MLA attention, a full-rank KDA gate and a latent MoE. No pinned graph has these tensors.", "watch": "report" + }, + "SegaForCausalLM": { + "model_type": "sega_tot_moe", + "family": "Sega 7.0 'Singularity-Infinity' (the123manaic) - 40 layers, hidden 4096, 64 heads. Reviewed as NOT an alias of a family we serve: model_type `sega_tot_moe` is not supported, the config carries non-standard `reasoning_passes` / `reasoning_speed_*` keys, and there is no auto_map (so it is not the remote-code case either - it is a custom architecture with a plain config).", + "watch": "report" } } }