# Hugging Face Transformers v3.5.0 — Release & Upgrade Intelligence
- **Product:** Hugging Face Transformers (https://huggingface.co)
- **Version:** v3.5.0
- **Released:** Nov 10, 2020
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/transformers/updates/v3.5.0/

## Executive Summary (TL;DR)
Hugging Face Transformers v3.5.0. Source highlight: Model versioning, TensorFlow encoder-decoder models, new scripts, refactor of the `generate` method

## New Features
- Add tensorflow 2.0 functionality for SOTA seq2seq transformers #7987 (@sshleifer)
- Masked Language Modeling: Add line by line option to mlm/plm scripts #8240 (@sgugger)
- Token classification: Add new token classification example #8340 (@sgugger)
- added qg evaluation notebook #7958 (@zolekode)
- [Notebooks] Add new encoder-decoder notebooks #8246 (@patrickvonplaten)

## Improvements
- changes made by the HuggingFace team will be way clearer – we can perform updates to the models to ensure they work well with the library(ies) (you'll be able to opt out from those changes)
- [s2s] create doc for pegasus/fsmt replication #7934 (@stas00)
- [s2s] test_distributed_eval #8315 (@stas00)
- [s2s] test_bash_script.py - actually learn something #8318 (@stas00)
- [s2s test_finetune_trainer] failing multigpu test #8400 (@stas00)

## Bug Fixes
- [s2s examples test] fix data path #8398 (@stas00)
- [s2s/distill] remove run_distiller.sh, fix xsum script #8412 (@sshleifer)
- Respect the 119 line chars #7928 (@LysandreJik)
- PPL guide code snippet minor fix #7938 (@joeddav)
- [ProphetNet] Add Question Generation Model + Test #7942 (@patrickvonplaten)
- [multiple models] skip saving/loading deterministic state_dict keys #7878 (@stas00)

## Upgrade Command
```bash
python -m pip install 'transformers==3.5.0'
```