pytorch/Phi-4-mini-instruct-AWQ-INT4 warn
Weights only ship in a format that can run code when loaded; loading it runs custom code from the repo; its license differs from its base model's. Plus 1 more issue.
Could not load this model from the Hugging Face API (private, gated, or nonexistent). Findings below are from our archive.
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 2026-08-26200,064-token embedding scanned · 0 undertrained · lineage consistent · pickle audit: 1 non-standard global(s) |
| 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.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 License differs from claimed parent (bsd-3-clause vs mit)
This model declares bsd-3-clause while its claimed base microsoft/Phi-4-mini-instruct 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.
info Embedding-norm glitch scan clean
No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (2.820). The glitch-token data-corruption class has no candidate surface in this model.
medium Pickle references non-standard globals
The pickle imports globals outside the standard torch/numpy/collections set: torchao.quantization.Int4Tensor. Common in full-model (non-state-dict) saves — each is code that runs at load time. Review before loading, or demand a safetensors release.
info Weights consistent with claimed parent microsoft/Phi-4-mini-instruct
Mean cosine similarity of 64 sampled token-embedding rows against microsoft/Phi-4-mini-instruct is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).
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.
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 pytorch/Phi-4-mini-instruct-AWQ-INT4
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 | phi3 · 32 layers · 3072-dim |
| vocabulary | 200,064 tokens |
| license | bsd-3-clause |
| serialization | no safetensors pickle custom code |
| chat template | present (chat_template.jinja) · sha256:febf589225c9728a |
| claimed lineage | microsoft/Phi-4-mini-instruct |
| lineage verified | consistent vs microsoft/Phi-4-mini-instruct — embedding-row cosine 1.000 |
| glitch-token surface | clean no undertrained tokens |
Full measured fingerprint
| architectures | Phi3ForCausalLM |
| library | transformers |
| pipeline | text-generation |
| repo files | 14 — pickle: pytorch_model.bin |
| revision | 82d711dc730a |
| HF snapshot | 204 downloads · 4 likes · updated 2025-10-09 · captured 2026-08-25 |
| pickle audit | pytorch_model.bin — 9 standard global(s), suspicious torchao.quantization.Int4Tensor |
| embedding tensor | model.embed_tokens.weight · BF16 · 200,064×3072 |
| embedding norms | median 2.82 · mean 4.796 |
| lineage check | consistent — cosine 1 over 64 sampled rows vs microsoft/Phi-4-mini-instruct |
Battery runs (1)the run trace behind the findings — what each job measured
| battery | status | queued | duration | attempts |
|---|---|---|---|---|
| weights | complete | 2026-08-25 21:50 | 4m | 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.embed_tokens.weight · BF16 · 200,064×3072 |
| glitch surface | 0 undertrained, 0 plain-ASCII |
| lineage check | consistent — cosine 1 over 64 rows vs microsoft/Phi-4-mini-instruct |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/pytorch/Phi-4-mini-instruct-AWQ-INT4)