Model page

ByteDance-Seed/BAGEL-7B-MoT warn

downloads 673likes 1.2klicense apache-2.0arch bagelparams 14691.1Mupdated 2026-01-09

claims base: Qwen/Qwen2.5-7B-Instruct · chat template: present · view on Hugging Face ↗

Scan coverage

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

BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-21
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-21152,064-token embedding scanned · 15184 undertrained · lineage inconclusive
Behavioral batteryLive-inference differentialsnot run

Findings

Scanned 2026-08-21 · published from a community scan.

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 15184 undertrained tokens (norm < 0.3× the vocabulary median of 3.022), including 757 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "TokenNameIdentifier", "ForCanBeConverted", "ForCanBeConvertedToF", "PostalCodesNL", "$PostalCodesNL", "<unk>", "thuisontvangst", "useRalative". In models where this class was tested behaviorally, such tokens silently rewrote user input into confident, schema-valid, wrong output. These are candidates from the weights alone; behavioral confirmation requires the behavioral battery.

How to fixruntime guardweight-level

Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.

  1. Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
  2. Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
  3. The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.

low Lineage vs claimed parent Qwen/Qwen2.5-7B-Instruct inconclusive

Mean embedding-row cosine similarity to the declared base is 0.568 — below the 0.8 typical of true derivatives but not low enough to call mislabeled. Heavy continued pretraining or vocabulary surgery can look like this; verify provenance before relying on the parent's safety or licensing posture.

How to fix

Fix or verify the `base_model` declaration so lineage checks can run.

  1. If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
  2. If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.

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 2026-08-21.

architecturebagel
parameters14691.1M
vocabulary152,064 tokens
licenseapache-2.0
serializationsafetensors
chat templatepresent · sha256:cd8e9439f0570856
claimed lineageQwen/Qwen2.5-7B-Instruct
lineage verifiedinconclusive vs Qwen/Qwen2.5-7B-Instruct — embedding-row cosine 0.568
glitch-token surface15,184 undertrained candidates, 757 plain-ASCII
Full measured fingerprint
architecturesBagelForConditionalGeneration
librarybagel-mot
pipelineany-to-any
repo files14
revision5019f57d168e
HF snapshot670 downloads · 1.2k likes · updated 2026-01-09 · captured 2026-08-21
embedding tensorlanguage_model.model.embed_tokens.weight · BF16 · 152,064×3584
embedding normsmedian 3.0221 · mean 2.6575
lineage checkinconclusive — cosine 0.568 over 64 sampled rows vs Qwen/Qwen2.5-7B-Instruct
glitch-token samples"TokenNameIdentifier", "ForCanBeConverted", "ForCanBeConvertedToF", "PostalCodesNL", "$PostalCodesNL", "<unk>", "thuisontvangst", "useRalative", "useRal", "prostituerte", "NdrFc", "_ComCallableWrapper"

Battery runs

The run trace behind the findings above: every deep-battery job for this model, with what each run measured or why it failed. Findings are only as good as the runs that produced them.

batterystatusqueueddurationattempts
weightscomplete2026-08-21 05:1371s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensorlanguage_model.model.embed_tokens.weight · BF16 · 152,064×3584
glitch surface15,184 undertrained, 757 plain-ASCII
lineage checkinconclusive — cosine 0.568 over 64 rows vs Qwen/Qwen2.5-7B-Instruct

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/ByteDance-Seed/BAGEL-7B-MoT/badge.svg)](https://ingot.tools/models/ByteDance-Seed/BAGEL-7B-MoT)
Gate it in CI