Model page

Skywork/Skywork-Critic-Llama-3.1-8B warn

downloads 363likes 13license otherarch llamaupdated 2024-09-29

claims base: meta-llama/Meta-Llama-3.1-8B-Instruct, 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 2026-08-22
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-22128,256-token embedding scanned · 496 undertrained · lineage consistent · pickle audit clean
Behavioral batteryLive-inference differentialsnot run

Findings

Scanned 2026-08-22 · published from a community scan.

medium Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (pytorch_model-00001-of-00033.bin, pytorch_model-00002-of-00033.bin, pytorch_model-00003-of-00033.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 License differs from claimed parent (other vs llama3.1)

This model declares other while its claimed base meta-llama/Meta-Llama-3.1-8B-Instruct declares llama3.1. Verify the re-license is permitted before commercial use.

How to fix

Verify the re-license is actually permitted before relying on it.

  1. Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
  2. If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 496 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-00033-of-00033.bin, pytorch_model-00001-of-00033.bin, pytorch_model-00002-of-00033.bin, pytorch_model-00003-of-00033.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 meta-llama/Meta-Llama-3.1-8B-Instruct

Mean cosine similarity of 64 sampled token-embedding rows against meta-llama/Meta-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 2026-08-22.

architecturellama · 32 layers · 4096-dim
vocabulary128,256 tokens
licenseother
serializationno safetensors pickle
chat templatepresent · sha256:e10ca381b1ccc5cf
claimed lineagemeta-llama/Meta-Llama-3.1-8B-Instruct, meta-llama/Llama-3.1-8B-Instruct
lineage verifiedconsistent vs meta-llama/Meta-Llama-3.1-8B-Instruct — embedding-row cosine 1.000
glitch-token surface496 undertrained candidates, 140 plain-ASCII
Full measured fingerprint
architecturesLlamaForCausalLM
pipelinetext-generation
repo files44 — pickle: pytorch_model-00001-of-00033.bin, pytorch_model-00002-of-00033.bin, pytorch_model-00003-of-00033.bin, pytorch_model-00004-of-00033.bin, pytorch_model-00005-of-00033.bin, pytorch_model-00006-of-00033.bin, pytorch_model-00007-of-00033.bin, pytorch_model-00008-of-00033.bin, pytorch_model-00009-of-00033.bin, pytorch_model-00010-of-00033.bin
revision825f34599593
HF snapshot367 downloads · 13 likes · updated 2024-09-29 · captured 2026-08-21
pickle auditpytorch_model-00033-of-00033.bin, pytorch_model-00001-of-00033.bin, pytorch_model-00002-of-00033.bin, pytorch_model-00003-of-00033.bin3 standard global(s)
embedding tensormodel.embed_tokens.weight · BF16 · 128,256×4096
embedding normsmedian 0.6847 · mean 0.6711
lineage checkconsistent — cosine 1 over 64 sampled rows vs meta-llama/Meta-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 05:322m1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, pickle-static-analysis, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · BF16 · 128,256×4096
glitch surface496 undertrained, 140 plain-ASCII
lineage checkconsistent — cosine 1 over 64 rows vs meta-llama/Meta-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/Skywork/Skywork-Critic-Llama-3.1-8B/badge.svg)](https://ingot.tools/models/Skywork/Skywork-Critic-Llama-3.1-8B)
Gate it in CI