Transformers Files

State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX

This is an exact mirror of the Transformers project, hosted at https://github.com/huggingface/transformers. SourceForge is not affiliated with Transformers.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
Patch release_ v5.5.2 source code.tar.gz	2026-04-09	17.5 MB	0
Patch release_ v5.5.2 source code.zip	2026-04-09	23.2 MB	0
README.md	2026-04-09	573 Bytes	0
Totals: 3 Items		40.7 MB	0

Small patch dedicated to optimizing gemma4, fixing inference with use_cache=False due to k/v states sharing between layers, as well as conversion mappings for some models that would inconsistently serialize their weight names. It contains the following PRs:

Add MoE to Gemma4 TP plan (#45219) by @sywangyi and @Cyrilvallez
[gemma4] Dissociate kv states sharing from the Cache (#45312) by @Cyrilvallez
[gemma4] Remove all shared weights, and silently skip them during loading (#45336) by @Cyrilvallez
Fix conversion mappings for vlms (#45340) by @Cyrilvallez

Source: README.md, updated 2026-04-09

Other Useful Business Software

Software Defined Storage

The layered architecture of QuantaStor provides solution engineers with unprecedented flexibility and application design options.

QuantaStor is a unified Software-Defined Storage platform designed to scale up and out to make storage management easy while reducing overall enterprise storage costs.

Learn More

FusionAuth: Authentication and User Management Software

Offer your users flexible authentication options, including passwords, passwordless, single sign-on (SSO), and multi-factor authentication (MFA).

FusionAuth adds login, registration, SSO, MFA, and a bazillion other features to your app in days - not months.

Learn More

Software Defined Storage

The layered architecture of QuantaStor provides solution engineers with unprecedented flexibility and application design options.

QuantaStor is a unified Software-Defined Storage platform designed to scale up and out to make storage management easy while reducing overall enterprise storage costs.

Learn More

Recommended Projects

Transformers in Time Series
A professionally curated list of awesome resources
GeoAI
GeoAI: Artificial Intelligence for Geospatial Data
Transformers-Interpret
Model explainability that works seamlessly with Hugging Face
DINOv3
Reference PyTorch implementation and models for DINOv3
pyAudioAnalysis
Python Audio Analysis Library: Feature Extraction, Classification

Transformers Files

State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX

Get an email when there's a new version of Transformers