Model page

NousResearch/Llama-2-7b-hf warn

No license declared — no usage rights by default; Special token id outside the vocabulary; glitch tokens that can silently corrupt ordinary input.

downloads 276.8klikes 176license none declaredarch llamaparams 6738.4Mupdated 2024-06-03

chat template: not found · view on Hugging Face ↗

Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-25
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-2532,000-token embedding scanned · 132 undertrained
Behavioral batteryLive-inference differentialsnot run

Ingot runs three batteries against a model. What each one checks →

Findings

Scanned 2026-08-25 · published from a community scan.

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.

  1. With no declared license you have no usage rights by default; treat the weights as all-rights-reserved.
  2. Open an issue or discussion on the repo asking the owner to declare a license, or use the licensed upstream/parent model instead.

medium Special token id outside the vocabulary

pad_token_id=32000 is outside the declared vocab_size of 32000. Runtimes either crash on it or silently ignore the setting (e.g. pad_token_id: -1), which breaks batching and stop handling.

How to fixingot patch

Align the stop-token declarations — a pure metadata fix to `generation_config.json` (and `config.json`).

  1. Identify the token the chat template actually ends assistant turns with (e.g. `<|eot_id|>`, `<end_of_turn>`, `<|im_end|>`) and make sure its id is in `generation_config.json`'s `eos_token_id` list.
  2. Keep `config.json`'s `eos_token_id` consistent with (or a subset of) `generation_config.json`'s — runtimes differ in which file they read.
  3. For the pad-equals-EOS hazard: repoint `pad_token` at a dedicated padding token before fine-tuning; serving is unaffected.
  4. Until the repo is fixed, pass explicit stop tokens to your serving stack (e.g. vLLM `stop_token_ids`, llama.cpp `--override-kv tokenizer.ggml.eos_token_id`).

medium Undertrained (glitch) token surface in vocabulary

Embedding-norm scan flagged 132 undertrained tokens (norm < 0.3× the vocabulary median of 1.100), including 14 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "<0xFE>", "<0xFF>", "<0xFB>", "<0xFC>", "<0xFD>", "<0xFA>", "Mediabestanden", "oreferrer". In models where this class was tested behaviorally, such tokens silently rewrote user input into confident, schema-valid, wrong output. These are candidates from the weights alone; 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.

  1. 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.
  2. 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.
  3. 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.

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 NousResearch/Llama-2-7b-hf

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 2026-08-25.

architecturellama · 32 layers · 4096-dim
parameters6738.4M
vocabulary32,000 tokens
licensenone declared
serializationsafetensors pickle
chat templatenone
glitch-token surface132 undertrained candidates, 14 plain-ASCII
Full measured fingerprint
architecturesLlamaForCausalLM
librarytransformers
pipelinetext-generation
repo files18 — pickle: pytorch_model-00001-of-00003.bin, pytorch_model-00002-of-00003.bin, pytorch_model-00003-of-00003.bin
revision8efe6c9b9365
HF snapshot276.8k downloads · 176 likes · updated 2024-06-03 · captured 2026-08-25
embedding tensormodel.embed_tokens.weight · F16 · 32,000×4096
embedding normsmedian 1.1001 · mean 1.08
lineage checkno claimed base model
glitch-token samples"<0xFE>", "<0xFF>", "<0xFB>", "<0xFC>", "<0xFD>", "<0xFA>", "Mediabestanden", "oreferrer", "Normdaten", "ITableView", "regnig", "demsel"
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 20:2622s1
weights run 2026-08-25 measurements
probes runglitch-norm-scan, zero-template-token-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · F16 · 32,000×4096
glitch surface132 undertrained, 14 plain-ASCII
lineage checknot checked (no claimed base model)

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/NousResearch/Llama-2-7b-hf/badge.svg)](https://ingot.tools/models/NousResearch/Llama-2-7b-hf)
Gate it in CI