Model page

unicamp-dl/ptt5-v2-base warn

Weights only ship in a format that can run code when loaded. Plus 1 minor note.

downloads 221likes 2license apache-2.0arch t5updated 2026-03-07

claims base: google-t5/t5-base · chat template: not found · view on Hugging Face ↗

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 inconsistent · 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 (1134.898). 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 Weights diverge from claimed parent google-t5/t5-base

This model declares google-t5/t5-base as its base (relation: unspecified), but mean cosine similarity of 64 sampled token-embedding rows against that parent is only 0.272 (true finetunes, merges, and quantizations sit above 0.8; independently trained weights sit near 0). Either the lineage label is wrong, or the model was so heavily re-trained, pruned, or distilled that the parent's properties (safety posture, evaluated behavior, licensing basis) should not be assumed to carry over. Verify provenance before relying on the parent's reputation.

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 · 12 layers · 768-dim
vocabulary32,128 tokens
licenseapache-2.0
serializationno safetensors pickle
chat templatenone
claimed lineagegoogle-t5/t5-base
lineage verifiedinconsistent vs google-t5/t5-base — embedding-row cosine 0.272
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesT5ForConditionalGeneration
librarytransformers
pipelinetext-generation
repo files11 — pickle: pytorch_model.bin
revision5f65a1c4c152
HF snapshot221 downloads · 2 likes · updated 2026-03-07 · captured 2026-08-25
pickle auditpytorch_model.bin3 standard global(s)
embedding tensorshared.weight · F32 · 32,128×768
embedding normsmedian 1134.8982 · mean 1109.8064
lineage checkinconsistent — cosine 0.2718 over 64 sampled rows vs google-t5/t5-base
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 21:5032s1
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 · 32,128×768
glitch surface0 undertrained, 0 plain-ASCII
lineage checkinconsistent — cosine 0.2718 over 64 rows vs google-t5/t5-base

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