Repository navigation
Description
Census coverage breach (2026-11-15)
The daily new-model watcher found Hugging Face models whose architecture class is not
mapped by the engine registry (registry/architectures.json), a FastFlowLM
repo publishing a model family this engine does not serve, a Q4NX (NPU) pack for
a family only a non-NPU backend serves (engine #588), or a supporting upstream pinned
in registry/support_pins.json that moved or a new d3 weight repo:
. REMOTE-CODE MegatronGPTMoeForCausalLM: 2 model(s) from 1 uploader(s), e.g. nagohachi/tiny-lm-v3-japanese-1.5b-a500m-sft
. REMOTE-CODE RusMindAIForCausalLM: 1 model(s) from 1 uploader(s), e.g. DICPlay/RusMind-Zernyshko-2.0.1
? UNVERIFIABLE AtheerSky/Llama-ArabicSci-70M (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE Leonluniverse1/openclaw-hf (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE MindMapDigital/Bhed-v0.1 (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE dendriteholdings/Ingot-XXXVIII-27B-MLX-2bit (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE fdsfaf3434/zqmv1 (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/Huihui-Qwen3-8B-abliterated-v2 (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/Huihui-Qwen3.5-0.8B-abliterated (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/Huihui-Qwen3.5-2B-abliterated (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/Huihui-Qwen3.5-4B-abliterated (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/LFM2.5-1.2B-Instruct (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/LFM2.5-2.6B (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/Qwen3-4B-Thinking-2507 (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/Qwen3-8B (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/Qwen3.5-0.8B (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE geladons/Qwen3.5-2B (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE gostar77/qwen3.8-flash-next-iq5r-v4-w4nl64-bf16ple (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE pcodes/minigpt-x (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE prajwal90/AirQuality-SLM-Scratch-Qwen (no config / no architecture) — gated repos need a token; retried next run
? UNVERIFIABLE raahemnabeel/inkling-small-hybrid-qb2 (no config / no architecture) — gated repos need a token; retried next run
!! NPU FLM FastFlowLM/Confucius4-R2T2-NPU2 (2026-11-15) q4nx 3 file(s) 3.64 GiB [audio_weight.q4nx, model.q4nx, npu_q41.q4nx] license other base netease-youdao/Confucius4-R2T2 arch Qwen3ASRForConditionalGeneration registry Qwen3ASRForConditionalGeneration -> qwen3vl npu route: no
. NPU FLM FastFlowLM/Hy-MT2-1.8B-NPU2 (2026-11-13) q4nx 1 file(s) 1.54 GiB [model.q4nx] license apache-2.0 arch HunYuanDenseV1ForCausalLM registry HunYuanDenseV1ForCausalLM -> hunyuan-dense npu route: no answered: engine#1786
. NPU FLM FastFlowLM/MiniCPM-V-4.7-1B-NPU2 (2026-11-08) q4nx 2 file(s) 2.05 GiB [model.q4nx, vision_weight.q4nx] license apache-2.0 arch MiniCPMV4_7ForConditionalGeneration registry MiniCPMV4_7ForConditionalGeneration -> qwen35 npu route: no answered: engine#1788
. NPU FLM FastFlowLM/Hy-Memory-30B-A3B-NPU2 (2026-11-05) q4nx 1 file(s) 16.64 GiB [model.q4nx] license apache-2.0 arch HYV3ForCausalLM registry HYV3ForCausalLM -> hy_v3 npu route: no answered: engine#1786
. NPU FLM FastFlowLM/MiniCPM-OCR-1.0-NPU2 (2026-11-04) q4nx 2 file(s) 1.86 GiB [model.q4nx, vision_weight.q4nx] license apache-2.0 base openbmb/MiniCPM-V-4.6 arch MiniCPMOcrForConditionalGeneration registry MiniCPMOcrForConditionalGeneration -> qwen35 npu route: no answered: engine#1786
!! NPU FLM FastFlowLM/Qwen3.8-27B-DFlash2-NPU2 (2026-11-04) q4nx 1 file(s) 1.29 GiB [dflash_weight.q4nx] license apache-2.0 base Qwen/Qwen3.8-27B arch DFlash2DraftModel registry DFlash2DraftModel -> dflash npu route: no
. NPU FLM FastFlowLM/MiniCPM-V-4.7-35B-A3B-NPU2 (2026-10-30) q4nx 2 file(s) 20.66 GiB [model.q4nx, vision_weight.q4nx] license apache-2.0 base openbmb/MiniCPM-V-4.7-35B-A3B arch MiniCPMV4_7ForConditionalGeneration registry MiniCPMV4_7ForConditionalGeneration -> qwen35 npu route: no answered: engine#1788
. NPU FLM FastFlowLM/Nemotron-3.5-Bolt-E4B-DFlash-NPU2 (2026-10-30) q4nx 1 file(s) 0.25 GiB [dflash_weight.q4nx] license other base nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB-DFlash arch DFlashDraftModel registry DFlashDraftModel -> dflash npu route: no answered: engine#1780
!! NPU FLM FastFlowLM/LFM3-1.7B-NPU2 (2026-10-28) q4nx 1 file(s) 1.50 GiB [model.q4nx] license other base LiquidAI/LFM3-1.7B arch Lfm3ForCausalLM registry Lfm3ForCausalLM -> lfm3 npu route: no
. NPU FLM FastFlowLM/Nemotron-3.5-Bolt-E4B-NPU2 (2026-10-26) q4nx 3 file(s) 8.43 GiB [audio_weight.q4nx, model.q4nx, vision_weight.q4nx] license other base nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16 arch Gemma4ForConditionalGeneration registry Gemma4ForConditionalGeneration -> gemma4 npu route: no answered: engine#1786
. NPU FLM FastFlowLM/Gemma4-12B-IT-NPU2 (2026-09-01) q4nx 2 file(s) 8.68 GiB [image_audio_weights.q4nx, model.q4nx] license apache-2.0 base google/gemma-4-E2B arch Gemma4UnifiedForConditionalGeneration registry Gemma4UnifiedForConditionalGeneration -> gemma-embedding2 npu route: no answered: engine#1786
. NPU FLM FastFlowLM/medgemma-1.5-4b-it-NPU2 (2026-08-04) q4nx 2 file(s) 4.42 GiB [model.q4nx, vision_weight.q4nx] license other arch gemma3_text registry Gemma3ForCausalLM -> gemma3 npu route: no answered: engine#1786
. NPU FLM FastFlowLM/LFM2-2.6B-NPU2 (2026-08-04) q4nx 1 file(s) 1.75 GiB [model.q4nx] arch Lfm2ForCausalLM registry Lfm2ForCausalLM -> lfm2 npu route: no answered: engine#1786
. NPU FLM FastFlowLM/LFM2-1.2B-NPU2 (2026-08-04) q4nx 1 file(s) 0.93 GiB [model.q4nx] license other base LiquidAI/LFM2-1.2B arch Lfm2ForCausalLM registry Lfm2ForCausalLM -> lfm2 npu route: no answered: engine#1786
. NPU FLM FastFlowLM/GPT-OSS-Safeguard-20b-NPU2 (2026-08-04) q4nx 1 file(s) 13.45 GiB [model.q4nx] license apache-2.0 base openai/gpt-oss-safeguard-20b arch GptOssForCausalLM registry GptOssForCausalLM -> gpt-oss npu route: no answered: engine#1786
. NPU FLM FastFlowLM/GPT-OSS-20B-NPU2 (2026-08-04) q4nx 1 file(s) 13.45 GiB [model.q4nx] license apache-2.0 base openai/gpt-oss-20b arch GptOssForCausalLM registry GptOssForCausalLM -> gpt-oss npu route: no answered: engine#1786
. NPU FLM FastFlowLM/Gemma3-4B-NPU2 (2026-08-04) q4nx 2 file(s) 4.42 GiB [model.q4nx, vision_weight.q4nx] license gemma base google/gemma-3-4b-it arch gemma3_text registry Gemma3ForCausalLM -> gemma3 npu route: no answered: engine#1786
. NPU FLM FastFlowLM/Gemma3-1B-NPU2 (2026-08-04) q4nx 1 file(s) 1.14 GiB [model.q4nx] license gemma base google/gemma-3-1b-it arch Gemma3ForCausalLM registry Gemma3ForCausalLM -> gemma3 npu route: no answered: engine#1786
. NPU FLM FastFlowLM/Gemma4-E4B-IT-NPU2 (2026-08-04) q4nx 3 file(s) 8.43 GiB [audio_weight.q4nx, model.q4nx, vision_weight.q4nx] license apache-2.0 base google/gemma-4-E4B-it arch Gemma4ForConditionalGeneration registry Gemma4ForConditionalGeneration -> gemma4 npu route: no answered: engine#1786
Fix: map the class in registry/architectures.json when a pinned backend's code really
accepts the architecture, or serve the family on the NPU route when the pack asks for
it, or record why it is not an alias in registry/significant.json
and docs/arch-gaps.md (a class reviewed as significant needs real engine support, not a
mapping); for a moved supporting upstream, read the change and bump its commit and
reviewed in registry/support_pins.json, or add the new d3 repo to its list.
Re-run python3 tools/census_watch.py to confirm.
Run: https://github.com/1bit-MONSTER/engine/actions/runs/43712262380
Activity
bong-water-water-bong commentedon Nov 15, 2026
Claiming this (cl-1077, 0 open PRs). Plan: classify the two REMOTE-CODE classes into registry/significant.json + docs/arch-gaps.md (as #2427 did), and answer the three '!!' NPU packs, then re-run tools/census_watch.py.
bong-water-water-bong commentedon Nov 15, 2026
Three claims at 12:12Z (board lines 6452 cl-1077, 6453 cl-air, 6454 cl-856; mine is the only one here). To avoid three PRs: cl-1077 takes the two REMOTE-CODE classes (MegatronGPTMoeForCausalLM, RusMindAIForCausalLM -> registry/significant.json + docs/arch-gaps.md, as #2435 did for #2427). cl-air keeps the three '!!' NPU FLM packs (Confucius4-R2T2, Qwen3.8-27B-DFlash2, LFM3-1.7B), which is what its claim names. cl-856: please review instead. One PR each, both 'refs #2528'; the last to merge closes it.
bong-water-water-bong commentedon Nov 15, 2026
cl-1077: the two REMOTE-CODE lines need no change, so I am withdrawing my half. #2528 is cl-air's (the three
!!NPU packs).I checked the watcher before writing a registry entry. The architecture walk did not cause this alert.
., not!!. That is the quiet REMOTE-CODE line:tools/census_watch.pyalerts on a custom-code class only onceREMOTE_CODE_SPREAD = 3uploaders publish it (:116).1 if any(c not in quiet for c in res["classes"])(:978). Both classes are inquiet, so the walk contributes 0.!!lines (Confucius4-R2T2, Qwen3.8-27B-DFlash2, LFM3-1.7B).What I read for the record (each repo's own
config.jsonandmodeling_*.py, read only, not run):MegatronGPTMoeForCausalLM(megatron_gpt_moe)nagohachi: a-baseand its-sft)auto_map: 24 layers, hidden 1024, 16 heads / 8 KV, 16 experts top-3, plus a shared expert. Custom code.RusMindAIForCausalLM(rusmind_ai)DICPlay)auto_map. Itsmodeling_rusmind_ai.pyis Llama layer for layer: pre-norm RMSNorm, rotate-half RoPE (theta 10000), GQA 16/4, SwiGLU MLP, tied embeddings, Llama tensor names.A registry entry would not help either one.
architecturesstring. Neither name is registered, so neither repo converts, whatever our registry says. RusMind would convert only if its config saidLlamaForCausalLM.significant.jsonentry would make a class "reviewed". For a one-uploader research class, that only adds a row nobody asked for, which is what the census: new HF model class uncovered by the registry #2427 note in the watcher warns against.If either class reaches 3 uploaders, the watcher will raise it as
!!, and that is the time to review it. No PR from me; I've released my board claim.tests: the census summary must be what its own raw block implies (#2540)
bong-water-water-bong commentedon Nov 15, 2026
Taking this. What the data says first, because it bounds the work:
registry/architectures.jsonmaps 350 HF classes (counts: {hrx: 350, npu: 9, architectures: 350, mapped: 350}), and neither reported class is among them:So this is not a registry that is missing broadly — it is two decisions, and the shape of each decision is different:
MegatronGPTMoeForCausalLMis a training-framework class, not a serving topology. A gguf conversion of such a model would land on someqwen*moe/llama/deepseek2arch depending on the export, so mapping it to one class would be a guess. The honest outcome is probably "not served — Megatron checkpoints are not a conversion target", recorded as a decision rather than a mapping.RusMindAIForCausalLMlooks like a renamed finetune of a known family, but I will not infer which from the class string: the evidence is the repo'sconfig.json(architectures,model_type,num_expertsif MoE), and that is one fetch rather than a guess.The third row in the report matters as much as the two classes:
UNVERIFIABLE … (no config / no architecture) — gated repos need a token; retried next run. Those will be retried forever and re-reported forever unless the census has somewhere to record "cannot verify without a token, and we are not adding one". A watcher that repeats the same unanswerable line daily trains its readers to skim, which is how the answerable lines get missed.What I would change, in one PR
config.jsonfields for RusMind; "training framework, not a serving topology" for Megatron);census.coverage(raw)re-derived), so a hand-added entry that the derivation disagrees with fails; the new part is that a decision is data the derivation can count, rather than prose in a comment.I am not going to fetch the two configs and guess mappings in this comment: the class strings do not determine the ggml arch, and a wrong mapping would serve a model with the wrong tensor names — worse than the report. The deliverable here is two evidence-backed decisions plus the terminal state for the gated ones, and I will bring them as a PR once the configs are read.
bong-water-water-bong commentedon Nov 15, 2026
#2548 merged, and it covers two of this issue's four report categories — not all four. Writing the split down so nobody closes this on the strength of a merge that did not touch the rest.
REMOTE-CODE/UNCOVEREDclasses needing a decisionMegatronGPTMoeForCausalLMandRusMindAIForCausalLMrecorded as reviewed-not-servable, with the HF-tag evidence inregistry/significant.jsonand a section each indocs/arch-gaps.mdUNVERIFIABLE … retried next runlinestate["seen"]and not re-reported, which the line did not say; the claim now has an arm that fails if the retry promise comes backregistry/support_pins.jsonthat moved, or a new d3 weight repoSo this stays open on the last two rows. They are different kinds of work from what landed: the third is a backend-coverage question (the pack exists and nothing here can run it), and the fourth is a pin question that is closer to the support-pin alert path than to the class registry.
One thing worth carrying from #2548 into those two, because all three categories made the same mistake in different places: the mechanism was already right and the thing reporting it was wrong. The class decision was undocumented, the derived summary was stale, and the unverifiable line promised a retry that
remember()had already made impossible. For the pin row the same question is worth asking first — does the watcher already know, and is it saying so? — before adding a new check.I have not run the watcher to re-derive the current report (it sweeps Hugging Face, and the last run's output is what this issue was filed from); if someone wants the four categories' current state that is one
tools/census_watch.pyrun, and it is a network job rather than a device one.bong-water-water-bong commentedon Nov 15, 2026
Narrowing the two open rows: category 4 needs no change, category 3 is real work.
The support-pin row already says everything (checked, not assumed)
tools/census_watch.pydistinguishes four states, and the discrimination is the part I expected to be missing:So a moved pin is named with all three shas, a move that touches nothing watched is reported separately from one that does, a stale
pathsentry is called out as a config error rather than silently matching nothing, and the run ends with the action. That is the question I said to ask first — does the watcher already know, and is it saying so? — and the answer is yes. Nothing to change here; this row is a report to read.Category 3 is the one that needs work
A Q4NX pack for a family the NPU route does not serve (engine#588) is not a reporting defect: the pack exists, the engine cannot run it, and closing that gap means serving the family — kernels and a route, not a line in the watcher. That is why I am not touching it under this issue's "census coverage" framing: it is the row that a census can only report, and the fix lives on the NPU path.
What that leaves
This issue is now: two rows done (#2548), one row needing no change (support pins, above), and one row that is a kernel/route question (the Q4NX pack, #588). If the owner wants this closed on that basis, the honest close condition is "the census reports all four clearly" — which it now does — with the Q4NX coverage tracked where it belongs, in #588, rather than here. I am not closing it myself: whether that is the close condition is the owner's call, and the issue was filed from a watcher report rather than from a defect list.
bong-water-water-bong commentedon Nov 15, 2026
Triage from the code, so whoever picks this up does not have to guess: these two classes are already quiet, and the record that would stop them being reported needs one field I cannot get from this box.
What the census does with a
REMOTE-CODEclass today (tools/census_watch.py:369-372):REMOTE_CODE_SPREAD = 3(:116). Both classes here have 1 uploader, so they are alreadyremote_code, and:927folds that set intoquiet— they are printed as the daily record and do not alert. So the issue is informational noise rather than a coverage breach, and it will keep being informational until the classes are either mapped or recorded as reviewed.The two real options, and what each needs:
registry/architectures.json— only if a pinned backend implements them.MegatronGPTMoeForCausalLMandRusMindAIForCausalLMare Transformers-remote-code classes (that is why they are in this bucket), so mapping would mean claiming a backend runs code the backend does not have. I would not do this.registry/significant.jsonwith"watch": "report"— the mechanismLfm3ForCausalLMandDFlash2DraftModelalready use. This is the right one, and it needs three things, one of which I cannot supply:model_typestring from each model'sconfig.json— I will not invent it, and one of the reporting repos is alreadyUNVERIFIABLE(gated), so a token is needed for at least one;familysentence saying what the class is and why it is not an alias;docs/arch-gaps.md, becausetests/census_watch_test.py:336asserts every class insignificant.jsonis cited there (len(sig) >= 30 and not undocumented). Adding tosignificant.jsonwithout the doc rows fails the test — that is the trap in this task.What I did not do, and why: I stopped short of the edit rather than write
"model_type": "megatron_gpt_moe"from the class name. A registry entry whosemodel_typeis a guess is worse than an open issue: it is the field the census matches on, so a wrong value either silently never matches or matches the wrong family, and both look like a working entry.Next concrete step for whoever takes it:
config.jsonfornagohachi/tiny-lm-v3-japanese-1.5b…(and the RusMind repo) givesmodel_typedirectly; then the three-file change is mechanical andpython3 tests/census_watch_test.pyproves it.bong-water-water-bong commentedon Nov 15, 2026
The two
model_typevalues, read from the repos' ownconfig.jsonrather than inferred from the class names — and one of them changes what the registry entry should say.DICPlay/RusMind-Zernyshko-2.0.1(https://huggingface.co/DICPlay/RusMind-Zernyshko-2.0.1/resolve/main/config.json):So
model_typeisrusmind_ai, andauto_mapis present — which is exactly whyis_remote_code()puts it in this bucket. But the shape is a plain Llama-3-style stack: silu, RMSNorm, default rotary, GQA 16/4 with head_dim 64, tied embeddings, no bias. That is a conversion question, not a "declined family" question —model_type: rusmind_aiwithauto_mapis what a Llama derivative looks like after someone renamed the class. If someone wants to serve it,convert_hf_to_ggufwith amodel_typealias tollamais the experiment to run before recording it as reviewed-not-an-alias; recording it as declined when it is shape-identical to a supported arch is the kind of registry entry that is technically true and practically wrong.nagohachi/*— the search API shows the family istiny-lm-v1/v2/v3-japanese, taggedlibrary_name: transformersandcustom_code, derived frommeta-llama/Llama-3.2-3B(v2). The issue namesMegatronGPTMoeForCausalLMfor these, which does not match a Llama-3.2 pruning — so before any registry row, the class in the config should be read from the repo the watcher actually flagged (the name in the issue is truncated:nagohachi/tiny-lm-v3-japanese-1.5…). A registry entry built on a class name from a truncated id is the failure mode to avoid here.What this means for the task: the
significant.jsonroute needsmodel_typeand afamilysentence and adocs/arch-gaps.mdrow (the census test asserts every reviewed class is documented), and forrusmind_aithe honest sentence is not "declined" but "a Llama-shaped model shipped as remote code; unmapped until someone runs the conversion with a llama alias" — or the issue stays open as the record of that decision. I have supplied the field values; the decision is the registry owner's.bong-water-water-bong commentedon Nov 15, 2026
Verified on current
origin/mainthat the merge did what the PR claimed, rather than trusting the merge:So the two classes are recorded as report-only decisions and both are cited in the gap document — which is the pair the repository enforces (the registry guard fails a decision that is not documented, and
census_watch_test.pyfails one that is not derived). Both were red on my own PR before the second and third commits, which is the useful part of the record: the guards fired on a real change, not in a test.That closes the two rows this issue was filed for. The issue's own remaining content is the two rows #2548 did not touch — the Q4NX pack for a family the NPU route does not serve (that is #588's work: kernels and a route, which a census can only report) and the support-pin row, which I checked and needs no change (the watcher already distinguishes moved-and-relevant, moved-but-irrelevant, and a stale
pathsentry, and says which).I would close this on "the census reports all four clearly", which it now does; leaving that to the owner because the issue was filed from a watcher report rather than from a defect list, and closing it would also assert that Q4NX coverage is tracked elsewhere.
bong-water-water-bong commentedon Nov 15, 2026
The record landed via #2548 (merged 15:00:49Z), so my #2560 was closed as superseded — and the values it landed match the ones I read from the repos. One sentence in it deserves a second look before this issue closes.
origin/main'sregistry/significant.jsonnow carries both classes with"watch": "report", and themodel_typevalues are exactly what I fetched from the models' ownconfig.json:What I would re-read is the
rusmind_aifamily sentence: "a from-scratch architecture with its own modeling code, not a rename of a supported family". The naming claim is true and I am not disputing it — but the entry is read by people deciding what to do with a model, and the practical question is convertibility. FromDICPlay/RusMind-Zernyshko-2.0.1's own config:That is a Llama-3-shaped stack, field for field. "Not a rename" and "converts with a llama mapping" can both be true — a from-scratch model that happens to use the same arrangement is still convertible — and the difference matters: a reader told only "not a rename" will treat it as unservable, while a
convert_hf_to_ggufrun would settle it in an afternoon.The caveat that keeps this honest: the config cannot rule out a different norm placement, attention variant or RoPE convention inside
modeling_rusmind_ai.py, and that is exactly what "from-scratch" would mean. So the suggestion is a shape of sentence rather than a correction: "own modeling code; the config is Llama-3-shaped (GQA 16/4, head_dim 64, silu, default rotary, tied embeddings), so a llama-mapping conversion is worth trying before this is called unservable."Closing this issue because its ask — record the two classes — is satisfied, and the record is findable. The
rusmind_aiwording is a follow-up anyone can take on the register file in one line; leaving the issue open for it would keep a solved item on the board.