Skip to main content

Lightning-fast LLM model introspection

Project description

rvnllm

rvnllm is a blazing-fast Python package for inspecting, diffing, and analyzing GGUF-based LLM model files.

Think ExifTool, but for large language models.

Features

  • Zero-copy GGUF model parsing
  • Tensor-level metadata inspection
  • Structural diffs between model files
  • Cross-platform wheels (Linux, macOS, Windows)

Installation

pip

pip install rvnllm

Build from source

git clone https://github.com/rvnllm/rvnllm.git
cd py/rvn_py
maturin build --release
pip install dist/*.whl

Usage example

import rvnllm

df = rvnllm.info("Llama-3-70B-Q4_0.gguf")
print(df.head())

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

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

rvnllm-0.1.14-cp313-cp313-manylinux_2_34_x86_64.whl (17.7 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.34+ x86-64

rvnllm-0.1.14-cp312-cp312-manylinux_2_34_x86_64.whl (17.7 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.34+ x86-64

rvnllm-0.1.14-cp311-cp311-manylinux_2_34_x86_64.whl (17.7 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.34+ x86-64

rvnllm-0.1.14-cp310-cp310-manylinux_2_34_x86_64.whl (17.7 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.34+ x86-64

rvnllm-0.1.14-cp39-cp39-manylinux_2_34_x86_64.whl (17.7 MB view details)

Uploaded CPython 3.9manylinux: glibc 2.34+ x86-64

rvnllm-0.1.14-cp38-cp38-manylinux_2_34_x86_64.whl (17.7 MB view details)

Uploaded CPython 3.8manylinux: glibc 2.34+ x86-64

File details

Details for the file rvnllm-0.1.14-cp313-cp313-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for rvnllm-0.1.14-cp313-cp313-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 c9e5f31b7f5d4be2ecb83fc653d67d3a16e95707dd291538ad548d020091ece9
MD5 8763645eda73f093318f7f8a0d1e227b
BLAKE2b-256 0829f561a55e55637fffc4e12c8dfcc4209efa48ea4ff4b648d8ffc8b8aafe3a

See more details on using hashes here.

File details

Details for the file rvnllm-0.1.14-cp312-cp312-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for rvnllm-0.1.14-cp312-cp312-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 fdc6ddfc8edd540f7d931cf83c737fbc5a2f08eb8f5059e831dba8cd9c7edce9
MD5 19097ebaef2c90cc6122d4eb9cdf451e
BLAKE2b-256 f6397729fa8acb1dca1727414f16dddf7136c332d55f1290b26f683ac74afdcd

See more details on using hashes here.

File details

Details for the file rvnllm-0.1.14-cp311-cp311-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for rvnllm-0.1.14-cp311-cp311-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 a0ecc94cc06cd6cde323a49db395f59d9650c412a7a2fcb6b8de381a1ca1b80e
MD5 aae14cfc4326c5f2f05dd0687ad7f8e0
BLAKE2b-256 99d2eb139c7e1748204f1a6bcd63253675bac3056e6d9cb385f13d2058f748ef

See more details on using hashes here.

File details

Details for the file rvnllm-0.1.14-cp310-cp310-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for rvnllm-0.1.14-cp310-cp310-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 b07e88fdcfb44881fd1275edbebeb70390aace4803d7edd17bd0e113c8843e7b
MD5 13f51c730d3bae49b8e20838fa434336
BLAKE2b-256 74900f3ed4069b87e656d72d6b26a08b2afba7069a333ce968745124cd619997

See more details on using hashes here.

File details

Details for the file rvnllm-0.1.14-cp39-cp39-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for rvnllm-0.1.14-cp39-cp39-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 a91be969806f2f0e31aa6153ed8454ad4cd9101f0ed30ac17c6129b5910fe18c
MD5 7c4383223ea30f09084aa1de1d063076
BLAKE2b-256 358165d60c532037a17bbf5800dad4bdb69e5ad243b50562c88c9678b93f8396

See more details on using hashes here.

File details

Details for the file rvnllm-0.1.14-cp38-cp38-manylinux_2_34_x86_64.whl.

File metadata

File hashes

Hashes for rvnllm-0.1.14-cp38-cp38-manylinux_2_34_x86_64.whl
Algorithm Hash digest
SHA256 7ef5feb6c8e1c29cd40df10358a5036790a84c71e0334f8304c68ae7732db0ae
MD5 2947e40c6458e62226e33a25da0e2834
BLAKE2b-256 9b8ed369fb41d3055f0e43f5b0f4bd725404fdb2f7d005c78d37c6db9ef72af9

See more details on using hashes here.

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