Model page

numind/NuExtract3-W4A16 warn

EOS ids disjoint between config.json and generation_config.json.

downloads 4.7klikes 6license apache-2.0arch qwen3_5params 4679.9Mupdated 2026-06-10

claims base: numind/NuExtract3 · chat template: present · view on Hugging Face ↗

Scan coverageStatic battery2026-08-27Weights battery2026-08-27Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-27
Weights batteryWeights forensics: no GPU, no downloadcomplete 2026-08-27248,320-token embedding scanned · 0 undertrained · lineage consistent
Behavioral batteryLive-inference differentialsnot run

Ingot runs three batteries against a model. What each one checks →

Findings

Scanned 2026-08-27 · published from a community scan.

medium EOS ids disjoint between config.json and generation_config.json

config.json declares eos_token_id [248046] while generation_config.json declares [248044] with no overlap. Runtimes read one or the other, so at least one of them stops generation on the wrong token (or never). Align both files on the token the chat template actually ends turns with.

How to fixingot patch

Align the stop-token declarations — a pure metadata fix to `generation_config.json` (and `config.json`).

  1. Identify the token the chat template actually ends assistant turns with (e.g. `<|eot_id|>`, `<end_of_turn>`, `<|im_end|>`) and make sure its id is in `generation_config.json`'s `eos_token_id` list.
  2. Keep `config.json`'s `eos_token_id` consistent with (or a subset of) `generation_config.json`'s — runtimes differ in which file they read.
  3. For the pad-equals-EOS hazard: repoint `pad_token` at a dedicated padding token before fine-tuning; serving is unaffected.
  4. Until the repo is fixed, pass explicit stop tokens to your serving stack (e.g. vLLM `stop_token_ids`, llama.cpp `--override-kv tokenizer.ggml.eos_token_id`).

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (0.652). The glitch-token data-corruption class has no candidate surface in this model.

info Weights consistent with claimed parent numind/NuExtract3

Mean cosine similarity of 64 sampled token-embedding rows against numind/NuExtract3 is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).

Put this result in your workflow

Check every checkpoint before it ships

Use the web app, API, CLI, or CI gate to scan candidate checkpoints and catch model drift before deployment. Public-model scans publish to the open database; paid plans add the volume needed for continuous checks.

Fix it

Some findings are metadata-level and patchable — apply the fixes to your local copy (your weights never leave your machine):

npx @ingotai/scan patch numind/NuExtract3-W4A16

Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.

Fingerprint

The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-27.

architectureqwen3_5 · 32 layers · 2560-dim
parameters4679.9M
vocabulary248,320 tokens
licenseapache-2.0
serializationsafetensors
chat templatepresent (chat_template.jinja) · sha256:31e44d28615d268e
claimed lineagenumind/NuExtract3
lineage verifiedconsistent vs numind/NuExtract3 — embedding-row cosine 1.000
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesQwen3_5ForConditionalGeneration
librarytransformers
pipelineimage-text-to-text
repo files27
revisionb5028670152c
HF snapshot4.7k downloads · 6 likes · updated 2026-06-10 · captured 2026-08-27
embedding tensormodel.language_model.embed_tokens.weight · BF16 · 248,320×2560
embedding normsmedian 0.6518 · mean 0.6557
lineage checkconsistent — cosine 1 over 64 sampled rows vs numind/NuExtract3
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-27 22:2761s1
weights run 2026-08-27 measurements
probes runglitch-norm-scan, zero-template-token-scan, lineage-norm-correlation
embedding tensormodel.language_model.embed_tokens.weight · BF16 · 248,320×2560
glitch surface0 undertrained, 0 plain-ASCII
lineage checkconsistent — cosine 1 over 64 rows vs numind/NuExtract3

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/numind/NuExtract3-W4A16/badge.svg)](https://ingot.tools/models/numind/NuExtract3-W4A16)
Gate it in CI