Model page

Youliang/llama3-8b-instruct-derta-100step warn

downloads 233likes 1license apache-2.0arch llamaparams 8030.3Mupdated 2024-07-21

claims base: meta-llama/Meta-Llama-3-8B-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 2026-08-21128,257-token embedding scanned · 461 undertrained
Behavioral batteryLive-inference differentialsnot run

Findings

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

medium Repo ships executable Python (trust_remote_code)

The repository contains custom code files that run in-process when loaded with trust_remote_code=True. Pin the revision hash and review the code before loading.

How to fix

Review and pin the custom code; never float on `main` with trust_remote_code=True.

  1. Read every `.py` file in the repo before first load — this code runs in your process.
  2. Pin the revision: `from_pretrained(model_id, revision="<commit sha>", trust_remote_code=True)` so a later push can't swap the code under you.
  3. Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.

medium License differs from claimed parent (apache-2.0 vs llama3)

This model declares apache-2.0 while its claimed base meta-llama/Meta-Llama-3-8B-Instruct declares llama3. 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 461 undertrained tokens (norm < 0.3× the vocabulary median of 0.601), including 131 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "$PostalCodesNL", "ForCanBeConverted", "TokenNameIdentifier", "useRalative", "ForCanBeConvertedToF", "PostalCodesNL", "ilmektedir", "CLIIIK". 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.

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
parameters8030.3M
vocabulary128,257 tokens
licenseapache-2.0
serializationsafetensors pickle custom code
chat templatepresent · sha256:ba03a121d097859c
claimed lineagemeta-llama/Meta-Llama-3-8B-Instruct
lineage verifiedunverified — weights battery pending
glitch-token surface461 undertrained candidates, 131 plain-ASCII
Full measured fingerprint
architecturesMyLlamaForCausalLM
librarytransformers
pipelinetext-generation
repo files15 — pickle: training_args.bin
revision815bb6a3f3d6
HF snapshot232 downloads · 1 likes · updated 2024-07-21 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · BF16 · 128,257×4096
embedding normsmedian 0.6012 · mean 0.5912
lineage checkparent weights unreadable (403 Forbidden for https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/model.safetensors.index.json (gated repo — the HF_TOKEN account has not accepted this repo's license, or the token lacks gated-repo read scope))
glitch-token samples"$PostalCodesNL", "ForCanBeConverted", "TokenNameIdentifier", "useRalative", "ForCanBeConvertedToF", "PostalCodesNL", "ilmektedir", "CLIIIK", "_ComCallableWrapper", "krvldkf", "webElementXpaths", "useRalativeImagePath"

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 05:1657s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · BF16 · 128,257×4096
glitch surface461 undertrained, 131 plain-ASCII
lineage checknot checked (parent weights unreadable (403 Forbidden for https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/resolve/main/model.safetensors.index.json (gated repo — the HF_TOKEN account has not accepted this repo's license, or the token lacks gated-repo read scope)))

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/Youliang/llama3-8b-instruct-derta-100step/badge.svg)](https://ingot.tools/models/Youliang/llama3-8b-instruct-derta-100step)
Gate it in CI