Inspect attached AI model deployment files without executing model code. DEEPBOM analyzes supported TFLite, ONNX, GGUF, SafeTensors, Core ML, and ExecuTorch files in the browser and reports SHA-256, serialized structure, tensor encodings, quantization evidence, and static findings. Explore Model IR tables and visualizations, and export SVG, PNG, Word-ready bundles, CycloneDX 1.7 artifact evidence, or SPDX 2.3 artifact inventories. Use Send PNG to chat to share a selected visualization or Save via ChatGPT to obtain a download link for a generated file when supported by the host. These actions share the generated export, not the model file. Results separate artifact defects, cautions, and evidence gaps, and explain what static analysis cannot establish. Use the local CLI or local MCP for confidential, very large, sharded, or multi-file artifacts.
How to use
- 1Add it in ChatGPT
Open DEEPBOM Artifact Evidence in ChatGPT's Plugin directory (button above), select + to add it and sign in if asked.
- 2Use it in a chat
Type @ in the composer and pick DEEPBOM Artifact Evidence, or start your message with its name. ChatGPT may also suggest it when it fits what you ask.
Skills 1
- deepbom-artifact-evidence
Inspect attached AI deployment artifacts with the DEEPBOM ChatGPT plugin. Use for static model structure, tensor encodings, quantization evidence, Model IR visualizations, and CycloneDX or SPDX artifact exports from supported TFLite, ONNX, GGUF, SafeTensors, Core ML, or ExecuTorch files. This workflow does not execute models or establish measured performance, accuracy, or regulatory compliance.
Things to ask
- “Inspect this ONNX model's quantization evidence and limits.”
- “List the tensor encodings in this GGUF artifact.”
- “Check this TFLite model for serialized payload defects.”