Model page

RadixArk/Kimi-K3-DSpark warn

downloads 2.8Mlikes 53license none declaredarch qwen3params 2249.3Mupdated 2026-08-16

chat template: not found · 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 downloadn/ano token-embedding tensor in the safetensors headers — not a text-token model (vision/audio/diffusion checkpoints have no vocabulary to scan)
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.

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.

  1. With no declared license you have no usage rights by default; treat the weights as all-rights-reserved.
  2. Open an issue or discussion on the repo asking the owner to declare a license, or use the licensed upstream/parent model instead.

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.

architectureqwen3 · 5 layers · 7168-dim
parameters2249.3M
vocabulary163,840 tokens
licensenone declared
serializationsafetensors custom code
chat templatenone
Full measured fingerprint
architecturesDSparkDraftModel
librarytransformers
pipelinetext-generation
repo files7
revision3c5bac301d9c
HF snapshot2.7M downloads · 52 likes · updated 2026-08-16 · captured 2026-08-21
weights batterytoken-embedding scan n/a — 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 07:421s1
weights run 2026-08-21 measurements

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/RadixArk/Kimi-K3-DSpark/badge.svg)](https://ingot.tools/models/RadixArk/Kimi-K3-DSpark)
Gate it in CI