alykassem/FLAN-T5-Paraphraser warn
Weights only ship in a format that can run code when loaded; loading it runs custom code from the repo. Plus 1 minor note.
Could not load this model from the Hugging Face API (private, gated, or nonexistent). Findings below are from our archive.
Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-25 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-2532,128-token embedding scanned · 30 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 2026-08-25 · published from a community scan.
medium Pickle-serialized weights, no safetensors
Weights ship only as pickle-based files (pytorch_model.bin, rng_state_0.pth, rng_state_1.pth, …). 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.
low Undertrained tokens in vocabulary (non-ASCII tail)
Embedding-norm scan flagged 30 undertrained tokens (norm < 0.3× the vocabulary median), but 0 decode to plain-ASCII strings, so exposure in English-language pipelines is limited. Behavioral confirmation requires the behavioral battery.
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.
- 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.
- 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.
- 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.
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 google/flan-t5-large
Mean cosine similarity of 64 sampled token-embedding rows against google/flan-t5-large is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).
How to fix
Fix or verify the `base_model` declaration so lineage checks can run.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.
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.
| architecture | t5 · 24 layers · 1024-dim |
| vocabulary | 32,128 tokens |
| license | apache-2.0 |
| serialization | no safetensors pickle custom code |
| chat template | none |
| claimed lineage | google/flan-t5-large |
| lineage verified | consistent vs google/flan-t5-large — embedding-row cosine 1.000 |
| glitch-token surface | 30 undertrained candidates, 0 plain-ASCII |
Full measured fingerprint
| architectures | T5ForConditionalGeneration |
| pipeline | text-generation |
| repo files | 15 — pickle: pytorch_model.bin, rng_state_0.pth, rng_state_1.pth, rng_state_2.pth, rng_state_3.pth, training_args.bin |
| revision | dfa3ba3b40f5 |
| HF snapshot | 349 downloads · 8 likes · updated 2025-01-06 · captured 2026-08-25 |
| pickle audit | pytorch_model.bin — 3 standard global(s) |
| embedding tensor | shared.weight · F32 · 32,128×1024 |
| embedding norms | median 316.5906 · mean 313.7707 |
| lineage check | consistent — cosine 1 over 64 sampled rows vs google/flan-t5-large |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 21:48 | 35s | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation |
| embedding tensor | shared.weight · F32 · 32,128×1024 |
| glitch surface | 30 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 1 over 64 rows vs google/flan-t5-large |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/alykassem/FLAN-T5-Paraphraser)