# Hugging Face Transformers v4.43.0 — Release & Upgrade Intelligence
- **Product:** Hugging Face Transformers (https://huggingface.co)
- **Version:** v4.43.0
- **Released:** Jul 23, 2024
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/transformers/updates/v4.43.0/

## Executive Summary (TL;DR)
Hugging Face Transformers v4.43.0. Source highlight: The Llama 3.1 models are released by Meta and come in three flavours: 8B, 70B, and 405B.

## Breaking Changes & Deprecations
- Breaking changes ### TextGenerationPipeline and tokenizer kwargs
- 🚨🚨 This PR changes the code to rely on the tokenizer's defaults when these flags are unset. This means some models using `TextGenerationPipeline` previously did not add a `<bos>` by default, which (negatively) impacted their performance. In practice, this is a breaking change.

## New Features
- Chameleon: add model  by @zucchini-nlp in #31534
- Add ZoeDepth  by @NielsRogge in #30136
- Adds final answer tool for all agents by @aymeric-roucher in #31703
- Add torch_empty_cache_steps to TrainingArguments (#31546)
- Add training support for SigLIP (#31495)
- Generate: Add new decoding strategy "DoLa" in `.generate()` (#29619)

## Bug Fixes
- Fix post gemma merge  by @ArthurZucker in #31660
- Fix float out of range in owlvit and owlv2 when using FP16 or lower precision  by @aliencaocao in #31657
- [docs] Llama3  by @stevhliu in #31662
- [HybridCache] Fix `get_seq_length` method  by @sanchit-gandhi in #31661
- don't zero out the attention_mask when using sliding window with flash attention  by @winglian in #31670
- Fix Gemma2 4d attention mask  by @hiyouga in #31674

## Upgrade Command
```bash
python -m pip install 'transformers==4.43.0'
```