voidful/Llama-3.1-TAIDE-R1-8B-Chat warn
No license declared — no usage rights by default; the chat template was dropped from its base model, which changes behavior; its tokenizer differs from its claimed base model. Plus 1 more issue.
claims base: deepseek-ai/DeepSeek-R1-Distill-Llama-8B, taide/Llama-3.1-TAIDE-LX-8B-Chat, meta-llama/Llama-3.1-8B-Instruct · chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-21Weights battery2026-08-21Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-21188,256-token embedding scanned · 519 undertrained · lineage consistent |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-21 · published from a community scan.
medium No license declared
The model card declares no license. You have no usage rights by default — treat as all-rights-reserved until the owner clarifies.
How to fix
Get a license from the owner or pick a licensed alternative — this is a legal gap, not a technical one.
- With no declared license you have no usage rights by default; treat the weights as all-rights-reserved.
- Open an issue or discussion on the repo asking the owner to declare a license, or use the licensed upstream/parent model instead.
medium Chat template dropped vs parent
deepseek-ai/DeepSeek-R1-Distill-Llama-8B ships a chat template; this repo does not. Serving stacks will silently fall back to a generic template, changing behavior. (In our 296-model census, 78% of pure quantization re-releases changed or dropped the template.)
How to fixingot patch
Restore the parent's chat template in `tokenizer_config.json` — a pure metadata fix.
- Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
- Or fix by hand: copy the `chat_template` value from the parent repo's `tokenizer_config.json` into this model's, and pin your serving stack to that file.
- If the drift was intentional (the author retrained on a new template), confirm that in the model card before "fixing" it — restoring the parent template on retrained weights changes behavior too.
medium Vocabulary size differs from claimed parent (188256 vs 128256)
A changed vocab means changed tokenization: strings will split differently than on deepseek-ai/DeepSeek-R1-Distill-Llama-8B, which can shift behavior on identifiers, codes, and non-English text.
How to fixweight-level
Not patchable: the vocab size mirrors the embedding matrix in the weights. Verify the change was intentional.
- Do not edit `vocab_size` in config.json to "match the parent" — it must equal the embedding table in the shipped weights or the model won't load.
- Diff the tokenizers (`tokenizer.json` / added_tokens) against the parent to see what was added or removed, and test your own identifiers, codes, and non-English text through both.
- If the drift is unexplained by the model card, treat tokenization-sensitive behavior as unvalidated on this model.
medium Undertrained (glitch) token surface in vocabulary
Embedding-norm scan flagged 519 undertrained tokens (norm < 0.3× the vocabulary median of 0.532), including 149 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "_ComCallableWrapper", "ektedir", "CLIIIK", "uyordu", "elementGuidId", "useRal", "krvldkf", "ForCanBeConvertedToF". 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 deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Mean cosine similarity of 44 sampled token-embedding rows against deepseek-ai/DeepSeek-R1-Distill-Llama-8B is 0.980 — 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.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.
Fix it
Some findings are metadata-level and patchable — apply the fixes to your local copy (your weights never leave your machine):
npx @ingotai/scan patch voidful/Llama-3.1-TAIDE-R1-8B-Chat
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.
| architecture | llama · 32 layers · 4096-dim |
| parameters | 8521.8M |
| vocabulary | 188,256 tokens |
| license | none declared |
| serialization | safetensors + gguf |
| chat template | none |
| claimed lineage | deepseek-ai/DeepSeek-R1-Distill-Llama-8B, taide/Llama-3.1-TAIDE-LX-8B-Chat, meta-llama/Llama-3.1-8B-Instruct |
| lineage verified | consistent vs deepseek-ai/DeepSeek-R1-Distill-Llama-8B — embedding-row cosine 0.980 |
| glitch-token surface | 519 undertrained candidates, 149 plain-ASCII |
Full measured fingerprint
| architectures | LlamaForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 19 |
| revision | fbfdba9e6fbf |
| HF snapshot | 2.2k downloads · 23 likes · updated 2025-02-25 · captured 2026-08-21 |
| embedding tensor | model.embed_tokens.weight · BF16 · 188,256×4096 |
| embedding norms | median 0.5323 · mean 0.663 |
| lineage check | consistent — cosine 0.9804 over 44 sampled rows vs deepseek-ai/DeepSeek-R1-Distill-Llama-8B |
| glitch-token samples | "_ComCallableWrapper", "ektedir", "CLIIIK", "uyordu", "elementGuidId", "useRal", "krvldkf", "ForCanBeConvertedToF", "useRalative", "sahuje", "$PostalCodesNL", "ecektir" |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-21 05:11 | 2m | 3 |
weights run 2026-08-21 — measurements
| probes run | glitch-norm-scan, lineage-norm-correlation |
| embedding tensor | model.embed_tokens.weight · BF16 · 188,256×4096 |
| glitch surface | 519 undertrained, 149 plain-ASCII |
| lineage check | consistent — cosine 0.9804 over 44 rows vs deepseek-ai/DeepSeek-R1-Distill-Llama-8B |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/voidful/Llama-3.1-TAIDE-R1-8B-Chat)