Model page

gaostar/DeViL-7B warn

Weights only ship in a format that can run code when loaded; loading it runs custom code from the repo; the chat template differs from its base model, which changes behavior. Plus 1 more issue.

downloads 15likes 1license apache-2.0arch devil_qwen2updated 2026-05-14

claims base: DAMO-NLP-SG/VideoLLaMA3-7B · chat template: present · 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 (pytorch_model-00001-of-00004.bin, pytorch_model-00002-of-00004.bin, pytorch_model-00003-of-00004.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 Repo ships executable Python (trust_remote_code)

The repository contains custom code files that run in-process when loaded with trust_remote_code=True. Pin the revision hash and review the code before loading.

How to fix

Review and pin the custom code; never float on `main` with trust_remote_code=True.

  1. Read every `.py` file in the repo before first load — this code runs in your process.
  2. Pin the revision: `from_pretrained(model_id, revision="<commit sha>", trust_remote_code=True)` so a later push can't swap the code under you.
  3. Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.

medium Chat template differs from claimed parent

The chat template does not match DAMO-NLP-SG/VideoLLaMA3-7B'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.

medium Architecture differs from claimed parent (devil_qwen2 vs videollama3_qwen2)

This model declares DAMO-NLP-SG/VideoLLaMA3-7B as its base, but its config declares architecture 'devil_qwen2' while the parent is 'videollama3_qwen2'. A finetune, merge, or quantization cannot change the architecture family — the lineage label is wrong or misleading, so treat provenance claims (training data, safety posture, licensing) as unverified.

How to fix

Fix or verify the `base_model` declaration so lineage checks can run.

  1. If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
  2. If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.

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 gaostar/DeViL-7B

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.

architecturedevil_qwen2 · 28 layers · 3584-dim
vocabulary152,064 tokens
licenseapache-2.0
serializationno safetensors pickle custom code
chat templatepresent · sha256:9cbf6eae47b8dde3
claimed lineageDAMO-NLP-SG/VideoLLaMA3-7B
lineage verifiedunverified — weights battery pending
Full measured fingerprint
architecturesDeViLQwen2ForCausalLM
librarytransformers
pipelinetext-generation
repo files15 — pickle: pytorch_model-00001-of-00004.bin, pytorch_model-00002-of-00004.bin, pytorch_model-00003-of-00004.bin, pytorch_model-00004-of-00004.bin
revision0a29fd82d951
HF snapshot15 downloads · 1 likes · updated 2026-05-14 · captured 2026-08-25
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightsqueued2026-08-25 22:250

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/gaostar/DeViL-7B/badge.svg)](https://ingot.tools/models/gaostar/DeViL-7B)
Gate it in CI