Skip to main content

astro-weights logo: astronaut with a gold visor and a violet chest patch

astro-weights

Small course corrections for open LLMs.
Agent-driven weight-space edits, exported as standard LoRA adapters.

PyPI version Python versions CI

PyPI · Changelog · Contributing

The goal: an agent proposes small, targeted low-rank edits to a model's weights, and the ones that hold up under paired tests are saved as plain PEFT LoRA adapters. Today (0.0.2) the library covers the edit core: build rank-1 edits, save and load them as LoRA adapters, and apply them to transformers models. LoRA is the output format because every serving stack already loads it (transformers, PEFT, vLLM, llama.cpp and the rest), so an edit needs no custom runtime: ship the adapter, load it like any other, and drop it to get the base model back.

Status: pre-alpha. 0.0.2 is on PyPI. The API will change without notice until 1.0.

Install

pip install astro-weights

To apply edits to transformers models, add the hf extra (pulls in torch, transformers and peft):

pip install "astro-weights[hf]"

Quick look

Build a rank-1 edit with numpy and save it as a LoRA adapter:

import numpy as np
from astro_weights.edits import Edit, masked_rank1
from astro_weights.export import save_peft

W0 = np.random.default_rng(0).standard_normal((16, 48), dtype=np.float32)
u = np.eye(16, dtype=np.float32)[0]
mask = np.ones(48, dtype=np.float32)
delta = masked_rank1("model.layers.1.mlp.down_proj", W0, u, mask, alpha=0.5)
save_peft(Edit(deltas=(delta,), base_model="org/name"), "my-edit")

Summarize and verify the saved adapter:

astro-weights inspect my-edit

Apply it to a transformers model (hf extra), and remove it again:

from astro_weights.export import load_peft
from astro_weights.runners.hf import apply, remove

peft_model = apply(model, load_peft("my-edit"))  # model: a transformers causal LM
model = remove(peft_model)  # base weights were never modified

apply matches the edit's layers to the model even when the two name them differently, as with a text-only and a multimodal load of the same checkpoint (model.layers.N... and model.language_model.layers.N...). It raises when a match is missing or ambiguous. resolve_modules(model, edit) shows the mapping without applying it.

Development

git clone https://github.com/astro-weights/astro-weights
cd astro-weights
uv sync
uv run pytest

See CONTRIBUTING.md for the full set of checks and how to send a pull request.

Citation

If you use astro-weights in your work, please cite it. The metadata is in CITATION.cff; on GitHub, use Cite this repository in the sidebar.

License

Apache-2.0.

The logo is based on the Noto Emoji "person astronaut" glyph, Copyright Google LLC, Apache-2.0. See docs/assets/LOGO-LICENSE.md.

Metadata

Release files for astro-weights 0.0.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for astro-weights 0.0.2
File Size Uploaded Provenance Actions
astro_weights-0.0.2.tar.gz 14.3 kB With provenance Details for astro_weights-0.0.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for astro-weights 0.0.2
File Interpreter ABI Platform Actions
astro_weights-0.0.2-py3-none-any.whl Python 3 none any Details for astro_weights-0.0.2-py3-none-any.whl

Total release size: 30.8 kB

Release files / astro_weights-0.0.2.tar.gz

Download URL astro_weights-0.0.2.tar.gz
Size 14.3 kB
Tags Source
SHA-256 checksum
How to use checksums
e3426acbcee503558c214bc5c399e7e4752f8d1255ae6e0ef6531766a7fa93a9
BLAKE2b-256 checksum
How to use checksums
e2458dc2cdc6cdbe74f6aca80db99820c4fabbd10b1a41acc3625d3ba0ea34cd
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 15, 2026.

Transparency log

Release files / astro_weights-0.0.2-py3-none-any.whl

Download URL astro_weights-0.0.2-py3-none-any.whl
Size 16.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
27740e042621fd181092df160c9ae0f9fb9a22c1d222808873b34ddf22c65111
BLAKE2b-256 checksum
How to use checksums
7eae3d752719de1b24521d3005d1bf5dab3c473abfd1492674c809c21b4db804
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 15, 2026.

Transparency log

Security for astro-weights 0.0.2

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

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for astro_weights-0.0.2.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 15, 2026.

Transparency log

A 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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page