# Hugging Face Transformers v4.42.0 — Release & Upgrade Intelligence
- **Product:** Hugging Face Transformers (https://huggingface.co)
- **Version:** v4.42.0
- **Released:** Jun 27, 2024
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/transformers/updates/v4.42.0/

## Executive Summary (TL;DR)
Hugging Face Transformers v4.42.0. Source highlight: The Gemma2 model was proposed in Gemma2: Open Models Based on Gemini Technology and Research by Gemma2 Team, Google.

## Breaking Changes & Deprecations
- Breaking changes ### Remove ConversationalPipeline and Conversation object
- This has the possibility of being a slight breaking change if users are creating models and relying on `out_indices` on being a tuple. As this property only happens when a new model is created, and not if it's saved and reloaded (because of the config), then I think this has a low chance of having much of an impact.
- Llama et al. / FSDP : Fix breaking change in 4.40 for FSDP  by @younesbelkada in #31161

## New Features
- Add gemma 2 by @ArthurZucker in #31659
- Add video modality for InstrucBLIP  by @zucchini-nlp in #30182
- Add LLaVa NeXT Video  by @zucchini-nlp in #31252
- Add Qwen2 GGUF loading support  by @Isotr0py in #31175
- FEAT / Trainer: LOMO optimizer support  by @younesbelkada in #30178
- Add TokenClassification for Mistral, Mixtral and Qwen2 (#29878)

## Improvements
- Quantized KV Cache  by @zucchini-nlp in #30483
- Docs / Quantization: refactor quantization documentation  by @younesbelkada in #30942
- Enable HF pretrained backbones  by @amyeroberts in #31145
- Reduce by 2 the memory requirement in `generate()` 🔥🔥🔥  by @Cyrilvallez in #30536

## Bug Fixes
- GGUF: Fix llama 3 GGUF  by @younesbelkada in #31358
- Fix llama gguf converter  by @SunMarc in #31575
- Add fixed resize and pad strategy for object detection  by @qubvel in #30742
- Enable dynamic resolution input for Swin Transformer and variants  by @the-neural-networker in #30656
- Add TokenClassification for Mistral, Mixtral and Qwen2  by @josephenguehard in #29878
- FIX / Quantization: Fix Dockerfile build  by @younesbelkada in #30890

## Upgrade Command
```bash
python -m pip install 'transformers==4.42.0'
```