Model page

TinyLlama/TinyLlama-1.1B-Chat-v1.0 warn

Glitch tokens confirmed behaviorally (echo test).

downloads 2.1Mlikes 1.7klicense apache-2.0arch llamaparams 1100.0Mupdated 2024-03-17

chat template: present · view on Hugging Face ↗

Scan coverageStatic battery2026-08-21Weights batterynot runBehavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-21
Weights batteryWeights forensics — no GPU, no downloadnot run
Behavioral batteryLive-inference differentialsnot run

Ingot runs three batteries against a model. What each one checks →

Findings

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

medium Glitch tokens confirmed behaviorally (echo test)

Asked to repeat its own undertrained tokens verbatim, the model failed on 8/13 while repeating 7/8 matched normal tokens correctly — e.g. "Mediabestanden" → ""Mediënmedewerker""; "autorytatywna" → ""autorypchieka""; "Webachiv" → ""<|assistant|> "<|user|> Can you please ". These strings, appearing in input as identifiers (usernames, SKUs, error codes), are rewritten silently. Greedy decoding, temperature 0, seed 0. Pipeline-corruption scenarios (the high-severity confirmation) are the next battery stage.

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.

Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
gpucomplete2026-08-21 05:2831s1
gpu run 2026-08-21 measurements
probes runglitch

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/TinyLlama/TinyLlama-1.1B-Chat-v1.0/badge.svg)](https://ingot.tools/models/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
Gate it in CI