Model page

openlm-research/open_llama_3b warn

Weights only ship in a format that can run code when loaded. Plus 1 minor note.

downloads 4.5klikes 166license apache-2.0arch llamaupdated 2023-06-16

chat template: not found · view on Hugging Face ↗

Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-25
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-2532,000-token embedding scanned · 113 undertrained · pickle audit clean
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 (pytorch_model.bin). 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.

low Undertrained tokens in vocabulary (non-ASCII tail)

Embedding-norm scan flagged 113 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.

info Pickle static analysis clean

Opcode-level parse of pytorch_model.bin (no code executed) found only standard serialization globals (4 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.

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 2026-08-25.

architecturellama · 26 layers · 3200-dim
vocabulary32,000 tokens
licenseapache-2.0
serializationno safetensors pickle
chat templatenone
glitch-token surface113 undertrained candidates, 0 plain-ASCII
Full measured fingerprint
architecturesLlamaForCausalLM
librarytransformers
pipelinetext-generation
repo files8 — pickle: pytorch_model.bin
revision141067009124
HF snapshot4.5k downloads · 166 likes · updated 2023-06-16 · captured 2026-08-25
pickle auditpytorch_model.bin4 standard global(s)
embedding tensormodel.embed_tokens.weight · F16 · 32,000×3200
embedding normsmedian 1.2821 · mean 1.2656
lineage checkno claimed base model
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 20:2617s1
weights run 2026-08-25 measurements
probes runglitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation
probes skippedtoken-decode: no tokenizer.json
embedding tensormodel.embed_tokens.weight · F16 · 32,000×3200
glitch surface113 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/openlm-research/open_llama_3b/badge.svg)](https://ingot.tools/models/openlm-research/open_llama_3b)
Gate it in CI