tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125 warn
Glitch tokens that can silently corrupt ordinary input; Glitch tokens confirmed behaviorally (echo test).
claims base: tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825, meta-llama/Llama-3.1-8B-Instruct · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-27Weights battery2026-08-21Behavioral batterycompletedetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-27 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-21128,256-token embedding scanned · 499 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | completefull differential battery (curated) |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-27 · published from a community scan.
medium Undertrained (glitch) token surface in vocabulary
Embedding-norm scan flagged 499 undertrained tokens (norm < 0.3× the vocabulary median of 0.694), including 148 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "$PostalCodesNL", "ForCanBeConverted", "TokenNameIdentifier", "useRalative", "ForCanBeConvertedToF", "PostalCodesNL", "ilmektedir", "CLIIIK". In models where this class was tested behaviorally, such tokens silently rewrote user input into confident, schema-valid, wrong output. These are candidates from the weights alone; behavioral confirmation requires the behavioral battery.
How to fixruntime guardweight-level
Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.
- Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
- Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
- The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.
info Weights consistent with claimed parent tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825
Mean cosine similarity of 64 sampled token-embedding rows against tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825 is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).
medium Glitch tokens confirmed behaviorally (echo test)
Asked to repeat its own undertrained tokens verbatim, the model failed on 14/16 while repeating 7/8 matched normal tokens correctly — e.g. "$PostalCodesNL" → ""$""; "ForCanBeConverted" → ""For"; "useRalative" → """. These strings, appearing in input as identifiers (usernames, SKUs, error codes), are rewritten silently. Greedy decoding, temperature 0, seed 0.
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
Check every checkpoint before it ships
Use the web app, API, CLI, or CI gate to scan candidate checkpoints and catch model drift before deployment. Public-model scans publish to the open database; paid plans add the volume needed for continuous checks.
Fingerprint
The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-21.
| architecture | llama · 32 layers · 4096-dim |
| parameters | 8030.3M |
| vocabulary | 128,256 tokens |
| license | llama3.1 |
| serialization | safetensors |
| chat template | none |
| claimed lineage | tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825, meta-llama/Llama-3.1-8B-Instruct |
| lineage verified | consistent vs tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825 — embedding-row cosine 1.000 |
| glitch-token surface | 499 undertrained candidates, 148 plain-ASCII |
Full measured fingerprint
| architectures | LlamaForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 17 |
| revision | 9e400db48fbb |
| HF snapshot | 638 downloads · 6 likes · updated 2026-08-13 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · BF16 · 128,256×4096 |
| embedding norms | median 0.6944 · mean 0.6797 |
| lineage check | consistent — cosine 1 over 64 sampled rows vs tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825 |
| glitch-token samples | "$PostalCodesNL", "ForCanBeConverted", "TokenNameIdentifier", "useRalative", "ForCanBeConvertedToF", "PostalCodesNL", "ilmektedir", "CLIIIK", "_ComCallableWrapper", "krvldkf", "webElementXpaths", "sahuje" |
Battery runs (2)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| gpu | complete | 2026-08-27 04:31 | 3m | 1 |
| weights | complete | 2026-08-21 05:14 | 4m | 1 |
gpu run 2026-08-27 — measurements
| probes run | glitch |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 128,256×4096 |
| glitch surface | 499 undertrained, 148 plain-ASCII |
| lineage check | consistent — cosine 1 over 64 rows vs tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125)