Model page

mlc-ai/Qwen2.5-7B-Instruct-q4f16_1-MLC warn

downloads 669likes 2license none declaredupdated 2025-09-07

claims base: Qwen/Qwen2.5-7B-Instruct · 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 downloadcomplete 2026-08-21no token vocabulary — pickle audit only · pickle audit clean
Behavioral batteryLive-inference differentialsnot run

Findings

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

medium Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (params_shard_0.bin, params_shard_1.bin, params_shard_10.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 No license declared

The model card declares no license. You have no usage rights by default — treat as all-rights-reserved until the owner clarifies.

How to fix

Get a license from the owner or pick a licensed alternative — this is a legal gap, not a technical one.

  1. With no declared license you have no usage rights by default; treat the weights as all-rights-reserved.
  2. Open an issue or discussion on the repo asking the owner to declare a license, or use the licensed upstream/parent model instead.

medium Chat template differs from claimed parent

The chat template does not match Qwen/Qwen2.5-7B-Instruct'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.

info Pickle static analysis clean

Opcode-level parse of params_shard_0.bin, params_shard_1.bin, params_shard_10.bin, params_shard_11.bin (no code executed) found only standard serialization globals (0 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.

low Pickle checkpoint only partially analyzable

Static analysis could not fully parse: params_shard_0.bin: legacy parse stopped after 0 pickle(s): unsupported pickle opcode 0x56 at 0, params_shard_1.bin: legacy parse stopped after 0 pickle(s): unsupported pickle opcode 0x6d at 0, params_shard_10.bin: legacy parse stopped after 0 pickle(s): unsupported pickle opcode 0x2d at 0, +1 more. Unparsed content is unverified.

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.

licensenone declared
serializationno safetensors pickle
chat templatepresent · sha256:d5495a1e5db06111
claimed lineageQwen/Qwen2.5-7B-Instruct
lineage verifiedunverified — weights battery pending
Full measured fingerprint
librarymlc-llm
repo files97 — pickle: params_shard_0.bin, params_shard_1.bin, params_shard_10.bin, params_shard_11.bin, params_shard_12.bin, params_shard_13.bin, params_shard_14.bin, params_shard_15.bin, params_shard_16.bin, params_shard_17.bin
revision691c5f251274
HF snapshot685 downloads · 2 likes · updated 2025-09-07 · captured 2026-08-21
weights batterytoken-embedding scan n/a — no token-embedding tensor found in the pickle checkpoint(s) — pickle checkpoint(s) statically analyzed anyway
pickle auditparams_shard_0.bin, params_shard_1.bin, params_shard_10.bin, params_shard_11.bin0 standard global(s) · legacy (pre-1.6) format, head-scan only

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
weightscomplete2026-08-21 05:136s1
weights run 2026-08-21 measurements
probes runpickle-static-analysis

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 mlc-ai/Qwen2.5-7B-Instruct-q4f16_1-MLC

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/mlc-ai/Qwen2.5-7B-Instruct-q4f16_1-MLC/badge.svg)](https://ingot.tools/models/mlc-ai/Qwen2.5-7B-Instruct-q4f16_1-MLC)
Gate it in CI