# Hugging Face Transformers v4.45.0 — Release & Upgrade Intelligence
- **Product:** Hugging Face Transformers (https://huggingface.co)
- **Version:** v4.45.0
- **Released:** Sep 25, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/transformers/updates/v4.45.0/

## Executive Summary (TL;DR)
Hugging Face Transformers v4.45.0. Source highlight: The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text + images in / text out). The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, ima

## New Features
- Add MLLama #33703, by @qubvel, @zucchini-nlp, @ArthurZucker
- Add Qwen2-Audio  by @faychu in #32137
- Add OLMoE  by @Muennighoff in #32406
- Llava Onevision: add model  by @zucchini-nlp in #32673
- Add new model  by @younesbelkada in #32615
- Add Descript-Audio-Codec model  by @kamilakesbi in #31494

## Improvements
- SoTA understanding of images of various resolution & ratio: Qwen2-VL achieves state-of-the-art performance on visual understanding benchmarks, including MathVista, DocVQA, RealWorldQA, MTVQA, etc.

## Bug Fixes
- Fix incorrect vocab size retrieval in GGUF config  by @Isotr0py in #32551
- 🌐 [i18n-KO] Translated `mask_generation.md` to Korean  by @jeongiin in #32257
- 🌐 [i18n-KO] Translated `idefics.md` to Korean  by @boyunJang in #32258
- 🌐 [i18n-KO] Translated `image_to_image.md` to Korean  by @shinhyunji36 in #32327
- Gemma2: add cache warning  by @zucchini-nlp in #32279
- enable xla fsdp  by @hanwen-sun in #32048

## Upgrade Command
```bash
python -m pip install 'transformers==4.45.0'
```