Model page

Qwen/Qwen3-Embedding-0.6B warn

downloads 7.7Mlikes 1.2klicense apache-2.0arch qwen3params 595.8Mupdated 2026-04-20

claims base: Qwen/Qwen3-0.6B-Base · chat template: present · view on Hugging Face ↗

Ingot findings

Static battery: 1 medium finding(s). Deep battery (behavioral differential, glitch-token pass) not yet run. Weights battery: embedding-norm scan over 151669 tokens (BF16, 1024-dim) found 0 undertrained candidates, 0 plain-ASCII. Lineage vs Qwen/Qwen3-0.6B-Base: consistent. Scanned 2026-08-20 (published from a community scan).

medium Vocabulary size differs from claimed parent (151669 vs 151936)

A changed vocab means changed tokenization: strings will split differently than on Qwen/Qwen3-0.6B-Base, which can shift behavior on identifiers, codes, and non-English text.

How to fixweight-level

Not patchable: the vocab size mirrors the embedding matrix in the weights. Verify the change was intentional.

  1. Do not edit `vocab_size` in config.json to "match the parent" — it must equal the embedding table in the shipped weights or the model won't load.
  2. Diff the tokenizers (`tokenizer.json` / added_tokens) against the parent to see what was added or removed, and test your own identifiers, codes, and non-English text through both.
  3. If the drift is unexplained by the model card, treat tokenization-sensitive behavior as unvalidated on this model.

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (0.968). The glitch-token data-corruption class has no candidate surface in this model.

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.

info Weights consistent with claimed parent Qwen/Qwen3-0.6B-Base

Mean cosine similarity of 64 sampled token-embedding rows against Qwen/Qwen3-0.6B-Base is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).

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 weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.

architectureqwen3 · 28 layers · 1024-dim
parameters595.8M
vocabulary151,669 tokens
licenseapache-2.0
serializationsafetensors
chat templatepresent · sha256:87a2728cb8dc9fe4
claimed lineageQwen/Qwen3-0.6B-Base
lineage verifiedconsistent vs Qwen/Qwen3-0.6B-Base — embedding-row cosine 1.000
glitch-token surfaceclean no undertrained tokens
Full fingerprint
architecturesQwen3ForCausalLM
librarysentence-transformers
pipelinefeature-extraction
repo files12
revision97b0c614be4d
HF snapshot7.7M downloads · 1.2k likes · updated 2026-04-20 · captured 2026-08-20
embedding tensorembed_tokens.weight · BF16 · 151,669×1024
embedding normsmedian 0.9677 · mean 0.9565
lineage checkconsistent — cosine 1 over 64 sampled rows vs Qwen/Qwen3-0.6B-Base

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/Qwen/Qwen3-Embedding-0.6B/badge.svg)](https://ingot.tools/models/Qwen/Qwen3-Embedding-0.6B)
Gate it in CI