concedo/koboldcpp warn
Weights only ship in a format that can run code when loaded; GGUF BPE tokenizer has no pre-tokenizer type. Plus 1 minor note.
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 2026-08-2650,266-token embedding scanned · 528 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.
low Undertrained tokens in vocabulary (non-ASCII tail)
Embedding-norm scan flagged 528 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.
- 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.
- 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.
- 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 (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.
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 concedo/koboldcpp
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 | opt · 1 layers · 4-dim |
| vocabulary | 50,266 tokens |
| license | other |
| serialization | gguf pickle |
| chat template | none |
| glitch-token surface | 528 undertrained candidates, 0 plain-ASCII |
Full measured fingerprint
| architectures | OPTForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 9 — pickle: pytorch_model.bin |
| revision | 6fd5154a4e91 |
| HF snapshot | 233 downloads · 5 likes · updated 2024-08-07 · captured 2026-08-25 |
| pickle audit | pytorch_model.bin — 3 standard global(s) |
| embedding tensor | model.decoder.embed_tokens.weight · F16 · 50,266×4 |
| embedding norms | median 0.041 · mean 0.0419 |
| 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 21:49 | 5s | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation, gguf-metadata |
| probes skipped | token-decode: no tokenizer.json |
| embedding tensor | model.decoder.embed_tokens.weight · F16 · 50,266×4 |
| glitch surface | 528 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/concedo/koboldcpp)