Model page

h2oai/h2ovl-mississippi-2b warn

downloads 746.9klikes 43license apache-2.0arch h2ovl_chatparams 2152.3Mupdated 2026-07-16

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 2026-08-22
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-2232,010-token embedding scanned · 201 undertrained
Behavioral batteryLive-inference differentialsnot run

Findings

Scanned 2026-08-22 · 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.

low Undertrained tokens in vocabulary (non-ASCII tail)

Embedding-norm scan flagged 201 undertrained tokens (norm < 0.3× the vocabulary median), but 0 decode to plain-ASCII strings, so exposure in English-language pipelines is limited. 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 2026-08-22.

architectureh2ovl_chat
parameters2152.3M
vocabulary32,010 tokens
licenseapache-2.0
serializationsafetensors custom code
chat templatepresent · sha256:794f441dbfdd1f1c
glitch-token surface201 undertrained candidates, 0 plain-ASCII
Full measured fingerprint
architecturesH2OVLChatModel
librarytransformers
pipelinetext-generation
repo files17
revision50fe0c0661b5
HF snapshot746.9k downloads · 43 likes · updated 2026-07-16 · captured 2026-08-21
embedding tensorlanguage_model.model.embed_tokens.weight · BF16 · 32,010×2560
embedding normsmedian 0.7332 · mean 0.712
lineage checkno claimed base model

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 07:4310s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
probes skippedtoken-decode: no tokenizer.json
embedding tensorlanguage_model.model.embed_tokens.weight · BF16 · 32,010×2560
glitch surface201 undertrained, 0 plain-ASCII
lineage checknot checked (no claimed base model)

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/h2oai/h2ovl-mississippi-2b/badge.svg)](https://ingot.tools/models/h2oai/h2ovl-mississippi-2b)
Gate it in CI