psingdev/smartCoderv2_16bit warn
Weights only ship in a format that can run code when loaded; Chat template ends turns with <|end|>, which is not a configured stop token; its license differs from its base model's. Plus 2 more issues.
claims base: unsloth/Phi-3-mini-4k-instruct-bnb-4bit · 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 2026-08-2632,064-token embedding scanned · 601 undertrained · lineage inconclusive · 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.
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 Chat template ends turns with <|end|>, which is not a configured stop token
The chat template terminates assistant turns with <|end|>, but the effective EOS set (config.json ∪ generation_config.json = [32000] → ["<|endoftext|>"]) never stops on it. Config-honoring runtimes generate past the terminator until the token budget is exhausted — runaway cost and self-continuing fake turns. Add <|end|>'s id to generation_config.json's eos_token_id.
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 License differs from claimed parent (apache-2.0 vs mit)
This model declares apache-2.0 while its claimed base unsloth/Phi-3-mini-4k-instruct-bnb-4bit declares mit. 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.
medium Chat template differs from claimed parent
The chat template does not match unsloth/Phi-3-mini-4k-instruct-bnb-4bit's. Template drift silently changes model behavior even when weights are identical — 37% of drifted derivatives in our census left it undisclosed. Diff the templates before deploying.
How to fixingot patch
Restore the parent's chat template in `tokenizer_config.json` — a pure metadata fix.
- Run `ingot patch <owner/model>` — the patch manifest carries the parent's template and applies it to a local copy's `tokenizer_config.json`.
- Or fix by hand: copy the `chat_template` value from the parent repo's `tokenizer_config.json` into this model's, and pin your serving stack to that file.
- If the drift was intentional (the author retrained on a new template), confirm that in the model card before "fixing" it — restoring the parent template on retrained weights changes behavior too.
medium Stop token dropped vs claimed parent but still used by the template
unsloth/Phi-3-mini-4k-instruct-bnb-4bit stops on [32000,32001,32007]; this repo only stops on [32000], losing <|assistant|> (32001), <|end|> (32007) — which this repo's own chat template still emits. Config-honoring runtimes will generate straight past it. Restore the lost id(s) to generation_config.json's eos_token_id.
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`).
low Undertrained tokens in vocabulary (non-ASCII tail)
Embedding-norm scan flagged 601 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.
low Lineage vs claimed parent unsloth/Phi-3-mini-4k-instruct-bnb-4bit inconclusive
Mean embedding-row cosine similarity to the declared base is 0.745 — below the 0.8 typical of true derivatives but not low enough to call mislabeled. Heavy continued pretraining or vocabulary surgery can look like this; verify provenance before relying on the parent's safety or licensing posture.
How to fix
Fix or verify the `base_model` declaration so lineage checks can run.
- If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
- If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.
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 psingdev/smartCoderv2_16bit
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 · 3072-dim |
| vocabulary | 32,064 tokens |
| license | apache-2.0 |
| serialization | no safetensors pickle |
| chat template | present · sha256:268b6082ceb7176d |
| claimed lineage | unsloth/Phi-3-mini-4k-instruct-bnb-4bit |
| lineage verified | inconclusive vs unsloth/Phi-3-mini-4k-instruct-bnb-4bit — embedding-row cosine 0.745 |
| glitch-token surface | 601 undertrained candidates, 0 plain-ASCII |
Full measured fingerprint
| architectures | MistralForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 11 — pickle: pytorch_model-00001-of-00002.bin, pytorch_model-00002-of-00002.bin |
| revision | ef9168fd74e7 |
| HF snapshot | 19 downloads · 0 likes · updated 2024-05-06 · 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 · F16 · 32,064×3072 |
| embedding norms | median 1.6499 · mean 1.5585 |
| lineage check | inconclusive — cosine 0.745 over 64 sampled rows vs unsloth/Phi-3-mini-4k-instruct-bnb-4bit |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 22:16 | 47s | 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 · F16 · 32,064×3072 |
| glitch surface | 601 undertrained, 0 plain-ASCII |
| lineage check | inconclusive — cosine 0.745 over 64 rows vs unsloth/Phi-3-mini-4k-instruct-bnb-4bit |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/psingdev/smartCoderv2_16bit)