t-tech/T-lite-it-2.1 warn
The chat template differs from its base model, which changes behavior; its tokenizer differs from its claimed base model.
claims base: Qwen/Qwen3-8B · chat template: present · view on Hugging Face ↗
Scan coverageStatic battery2026-08-21Weights batteryfailedBehavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-21 |
| Weights battery | Weights forensics — no GPU, no download | failed429 Too Many Requests for https://huggingface.co/api/models/t-tech/T-lite-it-2.1 |
| 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 Chat template differs from claimed parent
The chat template does not match Qwen/Qwen3-8B's. Template drift silently changes model behavior even when weights are identical — 37% of drifted derivatives in our census left it undisclosed. Diff the templates before deploying.
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 (151689 vs 151936)
A changed vocab means changed tokenization: strings will split differently than on Qwen/Qwen3-8B, 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.
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 t-tech/T-lite-it-2.1
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 | qwen3 · 36 layers · 4096-dim |
| parameters | 8188.7M |
| vocabulary | 151,689 tokens |
| license | apache-2.0 |
| serialization | safetensors |
| chat template | present · sha256:30a75d10e60b57e2 |
| claimed lineage | Qwen/Qwen3-8B |
| lineage verified | unverified — weights battery pending |
Full measured fingerprint
| architectures | Qwen3ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 15 |
| revision | d125c970c553 |
| HF snapshot | 370.6k downloads · 25 likes · updated 2025-12-23 · captured 2026-08-21 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/t-tech/T-lite-it-2.1)