Model page

reaperdoesntknow/Qemma-sft warn

Weights only ship in a format that can run code when loaded; Chat template ends turns with <end_of_turn>, which is not a configured stop token; its license differs from its base model's. Plus 2 more issues.

downloads 3.0klikes 0license osl-3.0arch gemma3_textupdated 2026-08-18

claims base: google/gemma-3-1b-it, Qwen/Qwen3-0.6B · chat template: present · 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 2026-08-25262,149-token embedding scanned · 0 undertrained · lineage inconclusive · pickle audit clean
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 Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (pytorch_model.bin, training_args.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.

medium Chat template ends turns with <end_of_turn>, which is not a configured stop token

The chat template terminates assistant turns with <end_of_turn>, but the effective EOS set (config.json ∪ generation_config.json = [1] → ["<eos>"]) 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_of_turn>'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`).

  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 License differs from claimed parent (osl-3.0 vs gemma)

This model declares osl-3.0 while its claimed base google/gemma-3-1b-it declares gemma. Verify the re-license is permitted before commercial use.

How to fix

Verify the re-license is actually permitted before relying on it.

  1. 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.
  2. If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.

medium Stop token dropped vs claimed parent but still used by the template

google/gemma-3-1b-it stops on [1,106]; this repo only stops on [1], losing <end_of_turn> (106) — 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`).

  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 Vocabulary size differs from claimed parent (262149 vs 262144)

A changed vocab means changed tokenization: strings will split differently than on google/gemma-3-1b-it, which can shift behavior on identifiers, codes, and non-English text.

How to fixweight-level

Not patchable: the vocab size mirrors the embedding matrix in the weights. Verify the change was intentional.

  1. Do not edit `vocab_size` in config.json to "match the parent" — it must equal the embedding table in the shipped weights or the model won't load.
  2. Diff the tokenizers (`tokenizer.json` / added_tokens) against the parent to see what was added or removed, and test your own identifiers, codes, and non-English text through both.
  3. If the drift is unexplained by the model card, treat tokenization-sensitive behavior as unvalidated on this model.

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.244). The glitch-token data-corruption class has no candidate surface in this model.

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.

low Lineage vs claimed parent google/gemma-3-1b-it inconclusive

Mean embedding-row cosine similarity to the declared base is 0.758 — 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.

  1. If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
  2. 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 reaperdoesntknow/Qemma-sft

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.

architecturegemma3_text · 26 layers · 1152-dim
vocabulary262,149 tokens
licenseosl-3.0
serializationno safetensors pickle
chat templatepresent (chat_template.jinja) · sha256:7de1c58e208eda46
claimed lineagegoogle/gemma-3-1b-it, Qwen/Qwen3-0.6B
lineage verifiedinconclusive vs google/gemma-3-1b-it — embedding-row cosine 0.758
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesGemma3ForCausalLM
librarytransformers
pipelinetext-generation
repo files15 — pickle: pytorch_model.bin, training_args.bin
revisionf873068b4b54
HF snapshot3.0k downloads · 0 likes · updated 2026-08-18 · captured 2026-08-25
pickle auditpytorch_model.bin3 standard global(s)
embedding tensormodel.embed_tokens.weight · F32 · 262,149×1152
embedding normsmedian 1.2435 · mean 1.2397
lineage checkinconclusive — cosine 0.7585 over 64 sampled rows vs google/gemma-3-1b-it
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 21:4681s1
weights run 2026-08-25 measurements
probes runglitch-norm-scan, zero-template-token-scan, pickle-static-analysis, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · F32 · 262,149×1152
glitch surface0 undertrained, 0 plain-ASCII
lineage checkinconclusive — cosine 0.7585 over 64 rows vs google/gemma-3-1b-it

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/reaperdoesntknow/Qemma-sft/badge.svg)](https://ingot.tools/models/reaperdoesntknow/Qemma-sft)
Gate it in CI