Model page

facebook/blenderbot-400M-distill warn

Weights only ship in a format that can run code when loaded.

downloads 10.0klikes 468license apache-2.0arch blenderbotupdated 2023-03-30

chat template: not found · view on Hugging Face ↗

Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-25
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-258,008-token embedding scanned · 0 undertrained · pickle audit clean
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.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 (2.840). 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.

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.

architectureblenderbot · 2 layers · 1280-dim
vocabulary8,008 tokens
licenseapache-2.0
serializationno safetensors pickle
chat templatenone
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesBlenderbotForConditionalGeneration
librarytransformers
repo files13 — pickle: pytorch_model.bin
revisioneaaf64e3be20
HF snapshot10.0k downloads · 468 likes · updated 2023-03-30 · captured 2026-08-25
pickle auditpytorch_model.bin3 standard global(s)
embedding tensormodel.shared.weight · F16 · 8,008×1280
embedding normsmedian 2.8397 · mean 2.7811
lineage checkno claimed base model
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 20:265s1
weights run 2026-08-25 measurements
probes runglitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation
embedding tensormodel.shared.weight · F16 · 8,008×1280
glitch surface0 undertrained, 0 plain-ASCII
lineage checknot checked (no claimed base model)

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/facebook/blenderbot-400M-distill/badge.svg)](https://ingot.tools/models/facebook/blenderbot-400M-distill)
Gate it in CI