# Hugging Face Transformers v4.29.0 — Release & Upgrade Intelligence
- **Product:** Hugging Face Transformers (https://huggingface.co)
- **Version:** v4.29.0
- **Released:** May 10, 2023
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/transformers/updates/v4.29.0/

## Executive Summary (TL;DR)
Hugging Face Transformers v4.29.0. Source highlight: Transformers Agent is a new API that lets you use the library and Diffusers by prompting an agent (which is a large language model) in natural language. That agent will then output code using a set of predefined tools, leveraging the appropriate (and state-of-the-art) models for the task the user wa

## Breaking Changes & Deprecations
- Breaking changes This releases has three breaking changes compared to version v4.28.0.
- This releases has three breaking changes compared to version v4.28.0.
- Finally, the third breaking change aims to harmonize the training procedure for most of recent additions in transformers. It should be users' responsibility to fill_mask the padding tokens of the labels with the correct value. This PR addresses the issue that was raised by other architectures such as Luke or Pix2Struct

## New Features
- Add Segment Anything Model (SAM)  by @ArthurZucker in #22654
- [`SAM`] Add sam doc  by @younesbelkada in #22984
- Add `automatic-mask-generation` pipeline for Segment Anything Model (SAM)  by @ArthurZucker in #22840
- Add RWKV-4 by @sgugger and @younesbelkada in #22797
- Add FocalNet  by @NielsRogge in #21532
- Add focalnet backbone  by @alaradirik in #23104

## Bug Fixes
- Fix SAM example in documentation  by @fxmarty in #22887
- Small sam patch  by @ArthurZucker in #22920
- 🚨🚨🚨 [`Pix2Struct`] Attempts to fix training issues 🚨🚨🚨  by @younesbelkada in #23004
- Change `torch_dtype` to `str` when `saved_model=True` in `save_pretrained` for TF models  by @ydshieh in #22740
- 🌐 [i18n-KO] Translated `training.mdx` to Korean  by @gabrielwithappy in #22670
- Remove `DS_BUILD_AIO=1`  by @ydshieh in #22741

## Upgrade Command
```bash
python -m pip install 'transformers==4.29.0'
```