Model page

OpenGVLab/InternVL2-2B warn

downloads 1.0Mlikes 81license mitarch internvl_chatparams 2205.8Mupdated 2025-03-25

claims base: OpenGVLab/InternViT-300M-448px, internlm/internlm2-chat-1_8b · 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 2026-08-2292,553-token embedding scanned · 765 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 765 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.

architectureinternvl_chat
parameters2205.8M
vocabulary92,553 tokens
licensemit
serializationsafetensors custom code
chat templatepresent · sha256:49aa7cb516942cc5
claimed lineageOpenGVLab/InternViT-300M-448px, internlm/internlm2-chat-1_8b
lineage verifiedunverified — weights battery pending
glitch-token surface765 undertrained candidates, 0 plain-ASCII
Full measured fingerprint
architecturesInternVLChatModel
librarytransformers
pipelineimage-text-to-text
repo files23
revisione4f6747bd20f
HF snapshot1.0M downloads · 81 likes · updated 2025-03-25 · captured 2026-08-21
embedding tensorlanguage_model.model.tok_embeddings.weight · BF16 · 92,553×2048
embedding normsmedian 0.7296 · mean 0.7091
lineage checkparent weights unreadable (no token-embedding tensor in the safetensors headers — not a text-token model (vision/audio/diffusion checkpoints have no vocabulary to scan))

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 07:4322s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
probes skippedtoken-decode: no tokenizer.json
embedding tensorlanguage_model.model.tok_embeddings.weight · BF16 · 92,553×2048
glitch surface765 undertrained, 0 plain-ASCII
lineage checknot checked (parent weights unreadable (no token-embedding tensor in the safetensors headers — not a text-token model (vision/audio/diffusion checkpoints have no vocabulary to scan)))

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/OpenGVLab/InternVL2-2B/badge.svg)](https://ingot.tools/models/OpenGVLab/InternVL2-2B)
Gate it in CI