Model page

taobao-mnn/Qwen3.5-27B-MNN warn

Weights only ship in a format that can run code when loaded; the chat template was dropped from its base model, which changes behavior.

downloads 17likes 0license apache-2.0updated 2026-03-04

claims base: Qwen/Qwen3.5-27B · chat template: not found · view on Hugging Face ↗

Scan coverageStatic battery2026-08-25Weights batteryqueuedBehavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-25
Weights batteryWeights forensics — no GPU, no downloadqueued
Behavioral batteryLive-inference differentialsnot run

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

Findings

Scanned 2026-08-25 · published from a community scan.

medium Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (embeddings_bf16.bin). Loading pickle executes arbitrary code from the file — prefer a safetensors release or load in a sandbox.

How to fix

Convert the weights to safetensors before loading them anywhere that matters.

  1. Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
  2. Convert locally in a sandbox: `pip install safetensors` and use `safetensors.torch.save_file` on a state dict loaded with `torch.load(..., weights_only=True)` (refuses most code-execution payloads), or use Hugging Face's `convert.py` space/script.
  3. Pin the exact revision hash you converted from, and load only your converted safetensors artifact from then on.

medium Chat template dropped vs parent

Qwen/Qwen3.5-27B ships a chat template; this repo does not. Serving stacks will silently fall back to a generic template, changing behavior. (In our 296-model census, 78% of pure quantization re-releases changed or dropped the template.)

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.

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 taobao-mnn/Qwen3.5-27B-MNN

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 2026-08-25.

licenseapache-2.0
serializationno safetensors pickle
chat templatenone
claimed lineageQwen/Qwen3.5-27B
lineage verifiedunverified — weights battery pending
Full measured fingerprint
pipelinetext-generation
repo files12 — pickle: embeddings_bf16.bin
revisiond0a9e927a110
HF snapshot17 downloads · 0 likes · updated 2026-03-04 · captured 2026-08-25
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightsqueued2026-08-25 22:210

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/taobao-mnn/Qwen3.5-27B-MNN/badge.svg)](https://ingot.tools/models/taobao-mnn/Qwen3.5-27B-MNN)
Gate it in CI