internlm/internlm2-1_8b warn
Weights only ship in a format that can run code when loaded; loading it runs custom code from the repo; glitch tokens that can silently corrupt ordinary input. Plus 1 minor note.
chat template: not found · view on Hugging Face ↗
Scan coverageStatic battery2026-08-25Weights battery2026-08-25Behavioral batterynot rundetails
| Battery | Looks at | Status |
|---|---|---|
| Static battery | Metadata & packaging | complete 2026-08-25 |
| Weights battery | Weights forensics — no GPU, no download | complete 2026-08-2592,544-token embedding scanned · 771 undertrained · pickle audit clean |
| Behavioral battery | Live-inference differentials | not run |
Ingot runs three batteries against a model. What each one checks →
Findings
Scanned 2026-08-25 · 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.
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.
low Padding token is the EOS token
The pad token and the (only) EOS token are the same. Fine-tuning frameworks mask pad positions out of the loss, so training on this checkpoint teaches the model to never emit EOS — the Phi-4 / Qwen 2.5 / DeepSeek R1 infinite-generation bug. Safe to serve, hazardous to fine-tune; repoint pad_token at a dedicated token first.
How to fixingot patch
Align the stop-token declarations — a pure metadata fix to `generation_config.json` (and `config.json`).
- 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.
- Keep `config.json`'s `eos_token_id` consistent with (or a subset of) `generation_config.json`'s — runtimes differ in which file they read.
- For the pad-equals-EOS hazard: repoint `pad_token` at a dedicated padding token before fine-tuning; serving is unaffected.
- 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 771 undertrained tokens (norm < 0.3× the vocabulary median of 0.721), including 300 plain-ASCII strings that can appear in ordinary input as identifiers — e.g. "[UNUSED_TOKEN_51]", "[UNUSED_TOKEN_113]", "[UNUSED_TOKEN_17]", "[UNUSED_TOKEN_25]", "[UNUSED_TOKEN_131]", "[UNUSED_TOKEN_33]", "[UNUSED_TOKEN_50]", "[UNUSED_TOKEN_7]". 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.
- 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.
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 internlm/internlm2-1_8b
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.
| architecture | internlm2 · 24 layers · 2048-dim |
| vocabulary | 92,544 tokens |
| license | other |
| serialization | no safetensors pickle custom code |
| chat template | none |
| glitch-token surface | 771 undertrained candidates, 300 plain-ASCII |
Full measured fingerprint
| architectures | InternLM2ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 13 — pickle: pytorch_model.bin |
| revision | d753f1de0510 |
| HF snapshot | 6.5k downloads · 32 likes · updated 2025-03-13 · captured 2026-08-25 |
| pickle audit | pytorch_model.bin — 3 standard global(s) |
| embedding tensor | model.tok_embeddings.weight · BF16 · 92,544×2048 |
| embedding norms | median 0.7211 · mean 0.7009 |
| lineage check | no claimed base model |
| glitch-token samples | "[UNUSED_TOKEN_51]", "[UNUSED_TOKEN_113]", "[UNUSED_TOKEN_17]", "[UNUSED_TOKEN_25]", "[UNUSED_TOKEN_131]", "[UNUSED_TOKEN_33]", "[UNUSED_TOKEN_50]", "[UNUSED_TOKEN_7]", "[UNUSED_TOKEN_36]", "[UNUSED_TOKEN_49]", "[UNUSED_TOKEN_22]", "[UNUSED_TOKEN_140]" |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 21:45 | 24s | 1 |
weights run 2026-08-25 — measurements
| probes run | glitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation |
| embedding tensor | model.tok_embeddings.weight · BF16 · 92,544×2048 |
| glitch surface | 771 undertrained, 300 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/internlm/internlm2-1_8b)