Model page

Cactus-Compute/needle2 warn

Weights only ship in a format that can run code when loaded.

downloads 10.0klikes 331license apache-2.0arch needleupdated 2026-09-03

chat template: not found · view on Hugging Face ↗

Scan coverageStatic battery2026-08-25Weights batteryn/aBehavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-25
Weights batteryWeights forensics: no GPU, no downloadn/arepo ships no scannable weights (no safetensors and no pickle checkpoints — GGUF/CoreML/other formats)
Behavioral batteryLive-inference differentialsnot run

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

Findings

Scanned 2026-08-25 · published from a community scan.

medium Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (checkpoints/needle2.pkl). Loading pickle executes arbitrary code from the file — prefer a safetensors release or load in a sandbox.

How to fix

Convert the weights to safetensors before loading them anywhere that matters.

  1. Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
  2. Convert locally in a sandbox: `pip install safetensors` and use `safetensors.torch.save_file` on a state dict loaded with `torch.load(..., weights_only=True)` (refuses most code-execution payloads), or use Hugging Face's `convert.py` space/script.
  3. Pin the exact revision hash you converted from, and load only your converted safetensors artifact from then on.

Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.

Put this result in your workflow

Check every checkpoint before it ships

Use the web app, API, CLI, or CI gate to scan candidate checkpoints and catch model drift before deployment. Public-model scans publish to the open database; paid plans add the volume needed for continuous checks.

Fingerprint

The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-25.

architectureneedle · 27 layers · 512-dim
vocabulary8,192 tokens
licenseapache-2.0
serializationno safetensors pickle
chat templatenone
Full measured fingerprint
architecturesNeedleForToolCalling
librarycactus-needle
pipelinetext-generation
repo files92 — pickle: checkpoints/needle2.pkl
revision98fbd955b034
HF snapshot33.9k downloads · 218 likes · updated 2026-08-20 · captured 2026-08-25
weights batterytoken-embedding scan n/a — repo ships no scannable weights (no safetensors and no pickle checkpoints — GGUF/CoreML/other formats)
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 19:000s1
weights run 2026-08-25 — 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/Cactus-Compute/needle2/badge.svg)](https://ingot.tools/models/Cactus-Compute/needle2)
Gate it in CI