Model page

unicamp-dl/ptt5-v2-large warn

Weights only ship in a format that can run code when loaded. 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 battery2026-08-26Weights battery2026-08-26Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-26
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-2632,128-token embedding scanned · 0 undertrained · lineage inconclusive · pickle audit clean
Behavioral batteryLive-inference differentialsnot 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.

  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.

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (683.871). 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.

low Lineage vs claimed parent google-t5/t5-large inconclusive

Mean embedding-row cosine similarity to the declared base is 0.439 — below the 0.8 typical of true derivatives but not low enough to call mislabeled. Heavy continued pretraining or vocabulary surgery can look like this; verify provenance before relying on the parent's safety or licensing posture.

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.

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.

architecturet5 · 24 layers · 1024-dim
vocabulary32,128 tokens
licenseapache-2.0
serializationno safetensors pickle
chat templatenone
claimed lineagegoogle-t5/t5-large
lineage verifiedinconclusive vs google-t5/t5-large — embedding-row cosine 0.440
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesT5ForConditionalGeneration
librarytransformers
pipelinetext-generation
repo files11 — pickle: pytorch_model.bin
revision0ab44d47331b
HF snapshot66 downloads · 1 likes · updated 2026-07-10 · captured 2026-08-25
pickle auditpytorch_model.bin3 standard global(s)
embedding tensorshared.weight · F32 · 32,128×1024
embedding normsmedian 683.8712 · mean 680.1307
lineage checkinconclusive — cosine 0.4395 over 64 sampled rows vs google-t5/t5-large
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 21:5751s1
weights run 2026-08-25 measurements
probes runglitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation
probes skippedtoken-decode: no tokenizer.json
embedding tensorshared.weight · F32 · 32,128×1024
glitch surface0 undertrained, 0 plain-ASCII
lineage checkinconclusive — cosine 0.4395 over 64 rows vs google-t5/t5-large

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/unicamp-dl/ptt5-v2-large/badge.svg)](https://ingot.tools/models/unicamp-dl/ptt5-v2-large)
Gate it in CI