Model Card — mstatt/surgeon-small-graph/model_edited.safetensors
This card is generated from the surgical record itself; the package's
lineage.intoto.jsonl is the signed source of truth (verify it free at
the Surgeon's public verifier or with the bundled verify_attestation.py).
Architecture
- Identification: Vision · CNN (74% confidence)
- Source format:
safetensors· Intended task: not declared - Source license: not declared on the Hub
- Lineage chain: 3 surgeries — prior signed by
ed25519:5e39faeb9ecc(FALCONS.AI Model Surgeon V6.98; 0 earlier operation(s) carried) · mstatt/surgeon-small-graph - Post-surgery totals: 166,030 parameters · 30 tensors
- Compute estimate: 0.000266 GFLOPs (comparison metric, not a measurement)
Provenance & operations
- Parents: mstatt/surgeon-small-graph/model_edited.safetensors
- Operations performed: excise×1, hub_push×1, load×1, reparent×1, replace×1
- Weight merges recorded: 0
- Quantized tensors (F32→F16): 0
Surgery Log (ordered)
- load — hub:mstatt/surgeon-small-graph/model_edited.safetensors (0.5 MB, safetensors)
- excise — temporal.cand.bias
- hub_push — mstatt/surgeon-small-graph ← 7 file(s) (attestation included)
- replace — law_head.bias := Weight-Tied LM Head
- reparent — convs.2.score -> temporal.score
Validation
- Tissue imaging: not run
- Structural integrity is testable offline via the packaged
load_and_test.py.
Compliance note
The signed attestation + this card together document model composition, modification history, and validation evidence — the record structure technical-documentation obligations (e.g. EU AI Act Annex IV) ask for. This is evidence, not legal advice.
Operated with Model Surgeon — verify this package at surgeon.falcons.ai/verify © 2026 FALCONS.AI — Model Surgeon record format. The model weights remain their owner's.
- Downloads last month
- 16
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support