allenai/tulu-2-70b warn
Weights only ship in a format that can run code when loaded; no license declared — no usage rights by default. 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 2026-08-2632,000-token embedding scanned · 137 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-00015.bin, pytorch_model-00002-of-00015.bin, pytorch_model-00003-of-00015.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 No license declared
The model card declares no license. You have no usage rights by default — treat as all-rights-reserved until the owner clarifies.
How to fix
Get a license from the owner or pick a licensed alternative — this is a legal gap, not a technical one.
- With no declared license you have no usage rights by default; treat the weights as all-rights-reserved.
- Open an issue or discussion on the repo asking the owner to declare a license, or use the licensed upstream/parent model instead.
low Undertrained tokens in vocabulary (non-ASCII tail)
Embedding-norm scan flagged 137 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-00015.bin, pytorch_model-00002-of-00015.bin, pytorch_model-00003-of-00015.bin, pytorch_model-00004-of-00015.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 2026-08-26.
| architecture | llama · 80 layers · 8192-dim |
| vocabulary | 32,000 tokens |
| license | none declared |
| serialization | no safetensors pickle |
| chat template | none |
| claimed lineage | meta-llama/Llama-2-70b-hf |
| lineage verified | unverified — weights battery pending |
| glitch-token surface | 137 undertrained candidates, 0 plain-ASCII |
Full measured fingerprint
| architectures | LlamaForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 26 — pickle: pytorch_model-00001-of-00015.bin, pytorch_model-00002-of-00015.bin, pytorch_model-00003-of-00015.bin, pytorch_model-00004-of-00015.bin, pytorch_model-00005-of-00015.bin, pytorch_model-00006-of-00015.bin, pytorch_model-00007-of-00015.bin, pytorch_model-00008-of-00015.bin, pytorch_model-00009-of-00015.bin, pytorch_model-00010-of-00015.bin |
| revision | be647298930c |
| HF snapshot | 102 downloads · 8 likes · updated 2024-04-19 · captured 2026-08-25 |
| pickle audit | pytorch_model-00001-of-00015.bin, pytorch_model-00002-of-00015.bin, pytorch_model-00003-of-00015.bin, pytorch_model-00004-of-00015.bin — 4 standard global(s) |
| embedding tensor | model.embed_tokens.weight · BF16 · 32,000×8192 |
| embedding norms | median 1.1528 · mean 1.1062 |
| 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 21:53 | 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 · 32,000×8192 |
| glitch surface | 137 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/allenai/tulu-2-70b)