Qwen/Qwen3-1.7B warn
claims base: Qwen/Qwen3-1.7B-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 151936 tokens (BF16, 2048-dim) found 3109 undertrained candidates, 21 plain-ASCII. Lineage vs Qwen/Qwen3-1.7B-Base: consistent. Scanned 2026-08-20 (published from a community scan).
medium Chat template differs from claimed parent
The chat template does not match Qwen/Qwen3-1.7B-Base's. Template drift silently changes model behavior even when weights are identical — 37% of drifted derivatives in our census left it undisclosed. Diff the templates before deploying.
How to fixingot patch
Restore the parent's chat template in `tokenizer_config.json` — a pure metadata fix.
- Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
- Or fix by hand: copy the `chat_template` value from the parent repo's `tokenizer_config.json` into this model's, and pin your serving stack to that file.
- If the drift was intentional (the author retrained on a new template), confirm that in the model card before "fixing" it — restoring the parent template on retrained weights changes behavior too.
medium Undertrained (glitch) token surface in vocabulary
Embedding-norm scan flagged 3109 undertrained tokens (norm < 0.3× the vocabulary median of 1.581), including 21 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "useRalative", "<unk>", "PostalCodesNL", "ForCanBeConverted", "ForCanBeConvertedToF", "useRal", "$PostalCodesNL", "thuisontvangst". 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 GPU deep 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.
- 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.
- 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.
- 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/Qwen3-1.7B-Base
Mean cosine similarity of 64 sampled token-embedding rows against Qwen/Qwen3-1.7B-Base is 0.996 — 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.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- 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.
| architecture | qwen3 · 28 layers · 2048-dim |
| parameters | 2031.7M |
| vocabulary | 151,936 tokens |
| license | apache-2.0 |
| serialization | safetensors |
| chat template | present · sha256:a55ee1b1660128b7 |
| claimed lineage | Qwen/Qwen3-1.7B-Base |
| lineage verified | consistent vs Qwen/Qwen3-1.7B-Base — embedding-row cosine 0.996 |
| glitch-token surface | 3,109 undertrained candidates, 21 plain-ASCII |
Full fingerprint
| architectures | Qwen3ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 12 |
| revision | 70d244cc86cc |
| HF snapshot | 6.0M downloads · 520 likes · updated 2025-07-26 · captured 2026-08-20 |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×2048 |
| embedding norms | median 1.5807 · mean 1.5394 |
| lineage check | consistent — cosine 0.996 over 64 sampled rows vs Qwen/Qwen3-1.7B-Base |
| glitch-token samples | "useRalative", "<unk>", "PostalCodesNL", "ForCanBeConverted", "ForCanBeConvertedToF", "useRal", "$PostalCodesNL", "thuisontvangst", "NdrFc", "sexdate", "wannonce", "davidjl" |
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 Qwen/Qwen3-1.7B
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/Qwen/Qwen3-1.7B)