Manhph2211/Q-HEART warn
Weights only ship in a format that can run code when loaded; loading it runs custom code from the repo; its license differs from its base model's. Plus 2 more issues.
claims base: meta-llama/Llama-3.2-1B-Instruct · chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-26Weights battery2026-08-26Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-26 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-26128,256-token embedding scanned · 0 undertrained · lineage consistent · pickle audit clean |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-26 · published from a community scan.
medium Pickle-serialized weights, no safetensors
Weights ship only as pickle-based files (pytorch_model.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.
- Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
- 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.
- 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.
- Read every `.py` file in the repo before first load — this code runs in your process.
- 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.
- Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.
medium License differs from claimed parent (apache-2.0 vs llama3.2)
This model declares apache-2.0 while its claimed base meta-llama/Llama-3.2-1B-Instruct declares llama3.2. Verify the re-license is permitted before commercial use.
How to fix
Verify the re-license is actually permitted before relying on it.
- Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
- If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.
medium Chat template dropped vs parent
meta-llama/Llama-3.2-1B-Instruct 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.
- 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.
medium Vocabulary size differs from claimed parent (32128 vs 128256)
A changed vocab means changed tokenization: strings will split differently than on meta-llama/Llama-3.2-1B-Instruct, which can shift behavior on identifiers, codes, and non-English text.
How to fixweight-level
Not patchable: the vocab size mirrors the embedding matrix in the weights. Verify the change was intentional.
- Do not edit `vocab_size` in config.json to "match the parent" — it must equal the embedding table in the shipped weights or the model won't load.
- Diff the tokenizers (`tokenizer.json` / added_tokens) against the parent to see what was added or removed, and test your own identifiers, codes, and non-English text through both.
- If the drift is unexplained by the model card, treat tokenization-sensitive behavior as unvalidated on this model.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (0.933). The glitch-token data-corruption class has no candidate surface in this model.
info Pickle static analysis clean
Opcode-level parse of pytorch_model.bin (no code executed) found only standard serialization globals (3 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.
info Weights consistent with claimed parent meta-llama/Llama-3.2-1B-Instruct
Mean cosine similarity of 64 sampled token-embedding rows against meta-llama/Llama-3.2-1B-Instruct is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).
Check every checkpoint before it ships
Use the web app, API, CLI, or CI gate to scan candidate checkpoints and catch model drift before deployment. Public-model scans publish to the open database; paid plans add the volume needed for continuous checks.
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 Manhph2211/Q-HEART
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 2026-08-26.
| architecture | qheart · 6 layers |
| vocabulary | 32,128 tokens |
| license | apache-2.0 |
| serialization | no safetensors pickle custom code |
| chat template | none |
| claimed lineage | meta-llama/Llama-3.2-1B-Instruct |
| lineage verified | consistent vs meta-llama/Llama-3.2-1B-Instruct — embedding-row cosine 1.000 |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | QHEARTForECGQA |
| library | transformers |
| pipeline | text-generation |
| repo files | 7 — pickle: pytorch_model.bin |
| revision | c64523ba904a |
| HF snapshot | 23 downloads · 1 likes · updated 2026-05-05 · captured 2026-08-25 |
| pickle audit | pytorch_model.bin — 3 standard global(s) |
| embedding tensor | llm.base_model.model.model.embed_tokens.weight · F32 · 128,256×2048 |
| embedding norms | median 0.9333 · mean 0.9298 |
| lineage check | consistent — cosine 1 over 64 sampled rows vs meta-llama/Llama-3.2-1B-Instruct |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 22:11 | 69s | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation |
| probes skipped | token-decode: no tokenizer.json |
| embedding tensor | llm.base_model.model.model.embed_tokens.weight · F32 · 128,256×2048 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 1 over 64 rows vs meta-llama/Llama-3.2-1B-Instruct |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/Manhph2211/Q-HEART)