Model page

HuggingFaceTB/SmolLM2-135M-Instruct pass

downloads 1.7Mlikes 401license apache-2.0arch llamaparams 134.5Mupdated 2025-09-22

claims base: HuggingFaceTB/SmolLM2-135M · chat template: present · view on Hugging Face ↗

Scan coverage

Ingot runs three batteries against a model. What each one checks →

BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-22
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-2249,152-token embedding scanned · 0 undertrained · lineage consistent
Behavioral batteryLive-inference differentialsnot run

Findings

Scanned 2026-08-22 · published from a community scan.

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (3.154). The glitch-token data-corruption class has no candidate surface in this model.

info Weights consistent with claimed parent HuggingFaceTB/SmolLM2-135M

Mean cosine similarity of 64 sampled token-embedding rows against HuggingFaceTB/SmolLM2-135M is 0.992 — 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.

  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.

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 2026-08-22.

architecturellama · 30 layers · 576-dim
parameters134.5M
vocabulary49,152 tokens
licenseapache-2.0
serializationsafetensors pickle
chat templatepresent · sha256:872be49dbb638044
claimed lineageHuggingFaceTB/SmolLM2-135M
lineage verifiedconsistent vs HuggingFaceTB/SmolLM2-135M — embedding-row cosine 0.992
glitch-token surfaceclean no undertrained tokens
Full measured fingerprint
architecturesLlamaForCausalLM
librarytransformers
pipelinetext-generation
repo files25 — pickle: training_args.bin
revision12fd25f77366
HF snapshot1.7M downloads · 400 likes · updated 2025-09-22 · captured 2026-08-21
embedding tensormodel.embed_tokens.weight · BF16 · 49,152×576
embedding normsmedian 3.1538 · mean 3.2021
lineage checkconsistent — cosine 0.9924 over 64 sampled rows vs HuggingFaceTB/SmolLM2-135M

Battery runs

The run trace behind the findings above: every deep-battery job for this model, with what each run measured or why it failed. Findings are only as good as the runs that produced them.

batterystatusqueueddurationattempts
weightscomplete2026-08-21 07:4218s1
weights run 2026-08-21 measurements
probes runglitch-norm-scan, lineage-norm-correlation
embedding tensormodel.embed_tokens.weight · BF16 · 49,152×576
glitch surface0 undertrained, 0 plain-ASCII
lineage checkconsistent — cosine 0.9924 over 64 rows vs HuggingFaceTB/SmolLM2-135M

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: pass

[![Ingot scan](https://ingot.tools/api/v1/models/HuggingFaceTB/SmolLM2-135M-Instruct/badge.svg)](https://ingot.tools/models/HuggingFaceTB/SmolLM2-135M-Instruct)
Gate it in CI