Model page

deb101/llama-8b-wiki10-31k-adapt-multilabel-classify warn

downloads 700likes 0license llama3.1arch llamaupdated 2026-08-03

claims base: meta-llama/Llama-3.1-8B-Instruct · chat template: present · view on Hugging Face ↗

Scan coverage

Ingot runs three batteries against a model. What each one checks →

BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-21
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-21128,256-token embedding scanned · 497 undertrained · lineage consistent · pickle audit clean
Behavioral batteryLive-inference differentialsnot run

Findings

Scanned 2026-08-21 · published from a community scan.

medium Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (pytorch_model.bin, training_args.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.

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 497 undertrained tokens (norm < 0.3× the vocabulary median of 0.685), including 140 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "ilmektedir", "$PostalCodesNL", "ForCanBeConvertedToF", "TokenNameIdentifier", "CLIIIK", "useRalative", "PostalCodesNL", "_ComCallableWrapper". In models where this class was tested behaviorally, such tokens silently rewrote user input into confident, schema-valid, wrong output. These are candidates from the weights alone; 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.

  1. 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.
  2. 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.
  3. 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 (5 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-3.1-8B-Instruct

Mean cosine similarity of 64 sampled token-embedding rows against meta-llama/Llama-3.1-8B-Instruct 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.

  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 2026-08-21.

architecturellama · 32 layers · 4096-dim
vocabulary128,256 tokens
licensellama3.1
serializationno safetensors pickle
chat templatepresent · sha256:e10ca381b1ccc5cf
claimed lineagemeta-llama/Llama-3.1-8B-Instruct
lineage verifiedconsistent vs meta-llama/Llama-3.1-8B-Instruct — embedding-row cosine 1.000
glitch-token surface497 undertrained candidates, 140 plain-ASCII
Full measured fingerprint
architecturesLlamaForCausalLM
librarytransformers
pipelinetext-generation
repo files12 — pickle: pytorch_model.bin, training_args.bin
revision3b722c24d19d
HF snapshot697 downloads · 0 likes · updated 2026-08-03 · captured 2026-08-21
pickle auditpytorch_model.bin5 standard global(s)
embedding tensorbase_model.base_model.model.model.embed_tokens.weight · BF16 · 128,256×4096
embedding normsmedian 0.6849 · mean 0.6713
lineage checkconsistent — cosine 1 over 64 sampled rows vs meta-llama/Llama-3.1-8B-Instruct
glitch-token samples"ilmektedir", "$PostalCodesNL", "ForCanBeConvertedToF", "TokenNameIdentifier", "CLIIIK", "useRalative", "PostalCodesNL", "_ComCallableWrapper", "ForCanBeConverted", "krvldkf", "sahuje", "webElementXpaths"

Battery runs

The run trace behind the findings above: every deep-battery job for this model, with what each run measured or why it failed. Findings are only as good as the runs that produced them.

batterystatusqueueddurationattempts
weightscomplete2026-08-21 05:132m1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, pickle-static-analysis, lineage-norm-correlation
embedding tensorbase_model.base_model.model.model.embed_tokens.weight · BF16 · 128,256×4096
glitch surface497 undertrained, 140 plain-ASCII
lineage checkconsistent — cosine 1 over 64 rows vs meta-llama/Llama-3.1-8B-Instruct

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/deb101/llama-8b-wiki10-31k-adapt-multilabel-classify/badge.svg)](https://ingot.tools/models/deb101/llama-8b-wiki10-31k-adapt-multilabel-classify)
Gate it in CI