Jaredquek/OpenhermesTrial warn
Weights only ship in a format that can run code when loaded; loading it runs custom code from the repo; its tokenizer differs from its claimed base model. Plus 1 more issue.
claims base: mistralai/Mistral-7B-v0.1 · chat template: present · 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 2026-08-2632,002-token embedding scanned · 194 undertrained · lineage consistent · 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-00001-of-00002.bin, pytorch_model-00002-of-00002.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.
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.
- Read every `.py` file in the repo before first load — this code runs in your process.
- 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.
- Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.
medium Vocabulary size differs from claimed parent (32002 vs 32000)
A changed vocab means changed tokenization: strings will split differently than on mistralai/Mistral-7B-v0.1, which can shift behavior on identifiers, codes, and non-English text.
How to fixweight-level
Not patchable: the vocab size mirrors the embedding matrix in the weights. Verify the change was intentional.
- Do not edit `vocab_size` in config.json to "match the parent" — it must equal the embedding table in the shipped weights or the model won't load.
- Diff the tokenizers (`tokenizer.json` / added_tokens) against the parent to see what was added or removed, and test your own identifiers, codes, and non-English text through both.
- If the drift is unexplained by the model card, treat tokenization-sensitive behavior as unvalidated on this model.
low Undertrained tokens in vocabulary (non-ASCII tail)
Embedding-norm scan flagged 194 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-00001-of-00002.bin, pytorch_model-00002-of-00002.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.
info Weights consistent with claimed parent mistralai/Mistral-7B-v0.1
Mean cosine similarity of 64 sampled token-embedding rows against mistralai/Mistral-7B-v0.1 is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).
medium GGUF stops on token 32000 (<|im_end|>), which the source repo does not use as EOS
tokenizer.ggml.eos_token_id is 32000 (<|im_end|>) but the source repo's effective EOS set is [2]. The conversion froze a wrong or since-fixed stop token — generation stops on the wrong token or not at all. Fix the id 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 Jaredquek/OpenhermesTrial
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 | mistral · 32 layers · 4096-dim |
| vocabulary | 32,002 tokens |
| license | apache-2.0 |
| serialization | gguf pickle custom code |
| chat template | present · sha256:153280e3ff55d19d |
| claimed lineage | mistralai/Mistral-7B-v0.1 |
| lineage verified | consistent vs mistralai/Mistral-7B-v0.1 — embedding-row cosine 1.000 |
| glitch-token surface | 194 undertrained candidates, 0 plain-ASCII |
Full measured fingerprint
| architectures | MistralForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 13 — pickle: pytorch_model-00001-of-00002.bin, pytorch_model-00002-of-00002.bin |
| revision | a951e7134c08 |
| HF snapshot | 20 downloads · 0 likes · updated 2023-12-30 · captured 2026-08-25 |
| pickle audit | pytorch_model-00001-of-00002.bin, pytorch_model-00002-of-00002.bin — 3 standard global(s) |
| embedding tensor | model.embed_tokens.weight · BF16 · 32,002×4096 |
| embedding norms | median 0.1792 · mean 0.1764 |
| lineage check | consistent — cosine 0.9998 over 64 sampled rows vs mistralai/Mistral-7B-v0.1 |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 22:14 | 47s | 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.embed_tokens.weight · BF16 · 32,002×4096 |
| glitch surface | 194 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 0.9998 over 64 rows vs mistralai/Mistral-7B-v0.1 |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/Jaredquek/OpenhermesTrial)