NousResearch/Nous-Hermes-2-Llama-2-70B warn
Weights only ship in a format that can run code when loaded; its license differs from its base model's. Plus 1 minor note.
claims base: meta-llama/Llama-2-70b-hf · 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 2026-08-2632,002-token embedding scanned · 136 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-00001-of-00029.bin, pytorch_model-00002-of-00029.bin, pytorch_model-00003-of-00029.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 License differs from claimed parent (apache-2.0 vs llama2)
This model declares apache-2.0 while its claimed base meta-llama/Llama-2-70b-hf declares llama2. Verify the re-license is permitted before commercial use.
How to fix
Verify the re-license is actually permitted before relying on it.
- Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
- If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.
low Undertrained tokens in vocabulary (non-ASCII tail)
Embedding-norm scan flagged 136 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-00029.bin, pytorch_model-00002-of-00029.bin, pytorch_model-00003-of-00029.bin, pytorch_model-00004-of-00029.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.
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 | llama · 80 layers · 8192-dim |
| vocabulary | 32,002 tokens |
| license | apache-2.0 |
| serialization | no safetensors pickle |
| chat template | none |
| claimed lineage | meta-llama/Llama-2-70b-hf |
| lineage verified | unverified — weights battery pending |
| glitch-token surface | 136 undertrained candidates, 0 plain-ASCII |
Full measured fingerprint
| architectures | LlamaForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 37 — pickle: pytorch_model-00001-of-00029.bin, pytorch_model-00002-of-00029.bin, pytorch_model-00003-of-00029.bin, pytorch_model-00004-of-00029.bin, pytorch_model-00005-of-00029.bin, pytorch_model-00006-of-00029.bin, pytorch_model-00007-of-00029.bin, pytorch_model-00008-of-00029.bin, pytorch_model-00009-of-00029.bin, pytorch_model-00010-of-00029.bin |
| revision | 3c42b2e32179 |
| HF snapshot | 99 downloads · 19 likes · updated 2024-02-12 · captured 2026-08-25 |
| pickle audit | pytorch_model-00001-of-00029.bin, pytorch_model-00002-of-00029.bin, pytorch_model-00003-of-00029.bin, pytorch_model-00004-of-00029.bin — 3 standard global(s) |
| embedding tensor | model.embed_tokens.weight · BF16 · 32,002×8192 |
| embedding norms | median 1.1524 · mean 1.1058 |
| lineage check | parent weights unreadable (403 Forbidden for https://huggingface.co/meta-llama/Llama-2-70b-hf/resolve/main/model.safetensors.index.json (gated repo — the HF_TOKEN account has not accepted this repo's license, or the token lacks gated-repo read scope)) |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 21:54 | 2m | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation |
| probes skipped | token-decode: no tokenizer.json |
| embedding tensor | model.embed_tokens.weight · BF16 · 32,002×8192 |
| glitch surface | 136 undertrained, 0 plain-ASCII |
| lineage check | not checked (parent weights unreadable (403 Forbidden for https://huggingface.co/meta-llama/Llama-2-70b-hf/resolve/main/model.safetensors.index.json (gated repo — the HF_TOKEN account has not accepted this repo's license, or the token lacks gated-repo read scope))) |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/NousResearch/Nous-Hermes-2-Llama-2-70B)