Inspect Ai Model Artifact
inspect_ai_model_artifactInspect GGUF, SafeTensors, ONNX, or TFLite artifacts via bounded reads to recover architecture, quantization, tensor metadata, and chat templates without loading full weights.
Instructions
Stream-inspect a local GGUF (.gguf), SafeTensors (.safetensors), ONNX (.onnx), or TensorFlow Lite (.tflite) model artifact in pure TypeScript using bounded file-descriptor slice reads without loading multi-gigabyte weight buffers into memory. Recovers model architecture, quantization/dtype summary, hyperparameters, tensor descriptors (names, dtypes, shapes, byte offsets/lengths), and embedded Jinja chat templates, system prompts, and special control tokens.
Example tool call
This call uses example arguments supplied in the tool’s input schema.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"path": "/artifacts/model.gguf",
"max_tensors": 500,
"extract_prompts": true,
"max_metadata_entries": 500
},
"name": "inspect_ai_model_artifact"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absolute filesystem path to the local .gguf, .safetensors, .onnx, or .tflite model artifact. | |
| max_tensors | No | Maximum number of tensor descriptors to return in the report (default 500). | |
| extract_prompts | No | Whether to extract embedded Jinja chat templates, system prompts, and control token definitions (default true). | |
| max_metadata_entries | No | Maximum number of key-value metadata entries to return (default 500). |