metrik-explorer

Architecture, parameter, and memory analysis — without a forward pass, without torch, and without a GPU.

$ metrik explore ./models/TinyLlama-1.1B

Reads safetensors headers (a length-prefixed JSON blob) and config.json. No tensor is ever deserialized, no torch is imported, and no forward pass happens.

One honest caveat: ModelFingerprint.weight_digest is a merkle over the weight files, because identity has to be content-based — a benchmark result attached to a name rather than a digest is unfalsifiable (artifacts.md §6.1). So the command does stream every weight byte through BLAKE3 once. It is I/O-bound, not compute-bound, and nothing is held in memory, but it is not free on a 140 GB directory. Header parsing alone is free, and that is what the structural analysis uses.

Emits four artifacts:

Artifact What it carries
ModelFingerprint identity: merkle over weight files, config digest, param split
ModelGraph one node per tensor — no edges, declared as an omission
GraphSummary role/dtype/depth breakdown plus evidenced observations
MemoryEstimate analytic weights + KV cache, with stated assumptions

What it deliberately does not do

  • No ParamStats. Per-tensor statistics need the weight data and a blob format that is still an open question (artifacts.md §8, question 1).
  • No graph edges. Headers describe storage, not dataflow. A topology needs torch and a forward pass, which is a different loader behind the same contract.
  • No measured numbers. MemoryEstimate is analytic by type and can never contain one (artifacts.md §5).

Role classification is name-based pattern matching, so GraphSummary.classification_confidence always reports what fraction of parameters it could not classify. A confident breakdown of a model the heuristic did not understand is worse than no breakdown.

Project links

Data verified by PyPI on
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for Hello-max-cloud-ally1010 from gravatar.com Hello-max-cloud-ally1010

Credits

Author: The Metrik Authors

GitHub Statistics

Data verified by PyPI on 
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

Apache-2.0
View SPDX License List

Requires

Python >=3.11

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

metrik_explorer-0.3.1.tar.gz (30.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

metrik_explorer-0.3.1-py3-none-any.whl (26.7 kB view details)

Uploaded Python 3

File details

Details for the file metrik_explorer-0.3.1.tar.gz.

File metadata

  • Download URL: metrik_explorer-0.3.1.tar.gz
  • Upload date:
  • Size: 30.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for metrik_explorer-0.3.1.tar.gz
Algorithm Hash digest
SHA256 d80ee96d4f9273817dcedb80414ae4c1bce539df3577768065ec804a0ede5638
MD5 1c1bd1b8a06c9790cbba58657de2ff35
BLAKE2b-256 c1bf635152297252e38d15b00d98118b9db093c9ccdaae3cfe945b3d7f12ca31

See more details on using hashes here.

Provenance

The following attestation bundles were made for metrik_explorer-0.3.1.tar.gz:

Publisher: release.yml on Asmodeus14/Metrik

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file metrik_explorer-0.3.1-py3-none-any.whl.

File metadata

File hashes

Hashes for metrik_explorer-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d4bfdf5de66db367301cd57155377e97732dda92b0457282b954eca522cd4af1
MD5 d5182b54bdde83f2fd624595b422a290
BLAKE2b-256 10f55cbe4f4b2850f6ba56e13ad9f9ebd2e9ae58cc9c237df5a0360da184d7ee

See more details on using hashes here.

Provenance

The following attestation bundles were made for metrik_explorer-0.3.1-py3-none-any.whl:

Publisher: release.yml on Asmodeus14/Metrik

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page