Model page

pytorch/SmolLM3-3B-INT8-INT4 warn

Weights only ship in a format that can run code when loaded; the weight files reference unusual code — review before loading. Plus 1 minor note.

downloads 129likes 39license apache-2.0arch smollm3updated 2025-09-11

claims base: HuggingFaceTB/SmolLM3-3B · chat template: present · view on Hugging Face ↗

Scan coverageStatic battery2026-08-26Weights battery2026-08-26Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-26
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-26no token vocabulary — pickle audit only · pickle audit: 1 non-standard global(s)
Behavioral batteryLive-inference differentialsnot 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.

  1. Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
  2. 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.
  3. 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`).

  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 Pickle references non-standard globals

The pickle imports globals outside the standard torch/numpy/collections set: torchao.quantization.IntxUnpackedToInt8Tensor. Common in full-model (non-state-dict) saves — each is code that runs at load time. Review before loading, or demand 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 pytorch/SmolLM3-3B-INT8-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.

architecturesmollm3 · 36 layers · 2048-dim
vocabulary128,256 tokens
licenseapache-2.0
serializationno safetensors pickle
chat templatepresent (chat_template.jinja) · sha256:3e0e275a527f2496
claimed lineageHuggingFaceTB/SmolLM3-3B
lineage verifiedunverified — weights battery pending
Full measured fingerprint
architecturesSmolLM3ForCausalLM
libraryoptimum-executorch
pipelinetext-generation
repo files10 — pickle: pytorch_model.bin
revision6ac5a613b3b1
HF snapshot129 downloads · 39 likes · updated 2025-09-11 · captured 2026-08-25
weights batterytoken-embedding scan n/a — no token-embedding tensor found in the pickle checkpoint(s) — pickle checkpoint(s) statically analyzed anyway
pickle auditpytorch_model.bin11 standard global(s), suspicious torchao.quantization.IntxUnpackedToInt8Tensor
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 21:524s1
weights run 2026-08-25 measurements
probes runpickle-static-analysis

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/pytorch/SmolLM3-3B-INT8-INT4/badge.svg)](https://ingot.tools/models/pytorch/SmolLM3-3B-INT8-INT4)
Gate it in CI