AutoWeight
Repair a fine-tuning regression in a local Hugging Face checkpoint while preserving behavior you want to keep. AutoWeight tests proposed weight edits on development examples and exports a standard Transformers checkpoint when one selected edit passes a separate confirmation set.
Try the offline demo
Use Python 3.11 or newer on macOS or Linux.
uv tool install 'auto-weight[hf,mcp]'
auto-weight demo
The demo generates a tiny model locally, runs two scripted edits, and prints the scores and the exported model path. For a pip installation, use python -m pip install 'auto-weight[hf,mcp]' in an active virtual environment.
Repair your own model
Bring a local safetensors checkpoint and labeled development and confirmation sets. For Codex or Claude Code, run auto-weight setup-runtime --input-root /path/to/repair-inputs using your existing input directory, then load the AutoWeight plugin from the repository. For terminal use, run auto-weight repair with a local Ollama proposer or use the manual proposal commands.
Metadata
Release files for auto-weight 0.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| auto_weight-0.4.0.tar.gz | 41.5 kB | With provenance | Details for auto_weight-0.4.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| auto_weight-0.4.0-py3-none-any.whl | Python 3 | none | any | Details for auto_weight-0.4.0-py3-none-any.whl |
Total release size: 81.2 kB
Release files / auto_weight-0.4.0.tar.gz
| Download URL | auto_weight-0.4.0.tar.gz |
|---|---|
| Size | 41.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9226bc2e5cd7e572867160544c92574a16df591587f883660c3b584c361ed8c9
|
|
BLAKE2b-256 checksum How to use checksums |
e4ba17782b3e088d230a76dc40b8c000d14abf7a492880c4e885088527f0ae8d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 6, 2026.
Transparency logRelease files / auto_weight-0.4.0-py3-none-any.whl
| Download URL | auto_weight-0.4.0-py3-none-any.whl |
|---|---|
| Size | 39.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5a632a8f151eb13e758ba736ec3140915a6dea20398b687faf4a967d9ea0523f
|
|
BLAKE2b-256 checksum How to use checksums |
7827ef728ad68a1e4a2bc9eeadda43c63c314d0b5532aa32bee84fedff7b8716
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 6, 2026.
Transparency logSecurity for auto-weight 0.4.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for auto_weight-0.4.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 6, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.