Qwen/Qwen2.5-1.5B-Instruct warn
claims base: Qwen/Qwen2.5-1.5B · 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, 1536-dim) found 0 undertrained candidates, 0 plain-ASCII. Lineage vs Qwen/Qwen2.5-1.5B: consistent. Scanned 2026-08-20 (published from a community scan).
medium Chat template differs from claimed parent
The chat template does not match Qwen/Qwen2.5-1.5B'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.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.029). 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.
- 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/Qwen2.5-1.5B
Mean cosine similarity of 64 sampled token-embedding rows against Qwen/Qwen2.5-1.5B is 0.999 — 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 | qwen2 · 28 layers · 1536-dim |
| parameters | 1543.7M |
| vocabulary | 151,936 tokens |
| license | apache-2.0 |
| serialization | safetensors |
| chat template | present · sha256:cd8e9439f0570856 |
| claimed lineage | Qwen/Qwen2.5-1.5B |
| lineage verified | consistent vs Qwen/Qwen2.5-1.5B — embedding-row cosine 1.000 |
| glitch-token surface | clean no undertrained tokens |
Full fingerprint
| architectures | Qwen2ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 10 |
| revision | 989aa7980e4c |
| HF snapshot | 10.0M downloads · 802 likes · updated 2024-09-25 · captured 2026-08-20 |
| embedding tensor | model.embed_tokens.weight · BF16 · 151,936×1536 |
| embedding norms | median 1.0285 · mean 1.0126 |
| lineage check | consistent — cosine 0.9995 over 64 sampled rows vs Qwen/Qwen2.5-1.5B |
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/Qwen2.5-1.5B-Instruct
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/Qwen2.5-1.5B-Instruct)