patrickbdevaney/WizardLM-1b-GGUF warn
Weights only ship in a format that can run code when loaded; GGUF BPE tokenizer has no pre-tokenizer type.
chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-26Weights battery2026-08-26Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-26 |
| Weights battery | Weights forensics: no GPU, no download | complete 2026-08-2649,153-token embedding scanned · 0 undertrained · pickle audit clean |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-26 · 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.
- Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
- 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.
- Pin the exact revision hash you converted from, and load only your converted safetensors artifact from then on.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (0.579). The glitch-token data-corruption class has no candidate surface in this model.
info Pickle static analysis clean
Opcode-level parse of pytorch_model.bin (no code executed) found only standard serialization globals (3 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.
medium GGUF BPE tokenizer has no pre-tokenizer type
tokenizer.ggml.pre is missing, so llama.cpp silently falls back to the default pre-tokenization regex and splits text differently than the original model — degraded quality, worst on numbers, code, and non-English text (the pre-May-2024 conversion signature). Reconvert with a current converter, or set the correct tokenizer.ggml.pre with gguf-py; no requant needed.
How to fixingot patch
Fix the GGUF's embedded metadata in place with gguf-py — template, EOS id, and pre-tokenizer are all metadata-editable; no requant needed.
- Template or EOS drift: copy the current values from the source repo and write them into the GGUF (`gguf_set_metadata.py` / gguf-py) — the tensor data is untouched.
- Missing pre-tokenizer type: reconvert with a current `convert_hf_to_gguf.py`, or set the correct `tokenizer.ggml.pre` for the architecture.
- Until the file is fixed, override at load time: llama.cpp `--override-kv tokenizer.ggml.eos_token_id=int:<id>` and `--chat-template-file <fixed.jinja>`.
- Prefer a re-upload from the quantizer once the source repo's fix lands — already-downloaded GGUFs never pick up upstream fixes on their own.
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.
Fix it
Some findings are metadata-level and patchable — apply the fixes to your local copy (your weights never leave your machine):
npx @ingotai/scan patch patrickbdevaney/WizardLM-1b-GGUF
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 2026-08-26.
| architecture | gpt_bigcode · 24 layers · 2048-dim |
| vocabulary | 49,153 tokens |
| license | bigscience-openrail-m |
| serialization | gguf pickle |
| chat template | none |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | GPTBigCodeForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 13 — pickle: pytorch_model.bin |
| revision | faef46a8f238 |
| HF snapshot | 40 downloads · 0 likes · updated 2024-02-27 · captured 2026-08-25 |
| pickle audit | pytorch_model.bin — 3 standard global(s) |
| embedding tensor | transformer.wte.weight · F16 · 49,153×2048 |
| embedding norms | median 0.579 · mean 0.6011 |
| lineage check | no claimed base model |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 22:04 | 20s | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation, gguf-metadata |
| embedding tensor | transformer.wte.weight · F16 · 49,153×2048 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | not checked (no claimed base model) |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/patrickbdevaney/WizardLM-1b-GGUF)