Model page

Qwen/Qwen2.5-14B-Instruct warn

downloads 2.8Mlikes 360license apache-2.0arch qwen2params 14770.0Mupdated 2024-09-25

claims base: Qwen/Qwen2.5-14B · 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 downloadqueued
Behavioral batteryLive-inference differentialsnot run

Findings

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

medium Chat template differs from claimed parent

The chat template does not match Qwen/Qwen2.5-14B'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.

  1. Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
  2. 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.
  3. 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.

low Partial glitch-token echo degradation

Echo failures on 6/16 undertrained tokens vs 0/8 controls — a differential exists but below the confirmation bar (≥50% glitch failures with clean controls).

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.

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.

architectureqwen2 · 48 layers · 5120-dim
parameters14770.0M
vocabulary152,064 tokens
licenseapache-2.0
serializationsafetensors
chat templatepresent · sha256:cd8e9439f0570856
claimed lineageQwen/Qwen2.5-14B
lineage verifiedunverified — weights battery pending
Full measured fingerprint
architecturesQwen2ForCausalLM
librarytransformers
pipelinetext-generation
repo files18
revisioncf98f3b3bbb4
HF snapshot2.8M downloads · 359 likes · updated 2024-09-25 · captured 2026-08-21

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
gpucomplete2026-08-21 21:322m1
weightsqueued2026-08-21 07:420
gpu run 2026-08-21 measurements
probes runglitch

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/Qwen2.5-14B-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:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/Qwen/Qwen2.5-14B-Instruct/badge.svg)](https://ingot.tools/models/Qwen/Qwen2.5-14B-Instruct)
Gate it in CI