# Hugging Face Transformers v3.3.0 — Release & Upgrade Intelligence
- **Product:** Hugging Face Transformers (https://huggingface.co)
- **Version:** v3.3.0
- **Released:** Sep 28, 2020
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/transformers/updates/v3.3.0/

## Executive Summary (TL;DR)
Hugging Face Transformers v3.3.0. Source highlight: The RAG model is a retrieval-augmented generation model that can be leveraged for question-answering tasks using `RagTokenForGeneration` or `RagSequenceForGeneration` as proposed in Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks by Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fa

## New Features
- [RAG] Add `attention_mask` to RAG generate #7373 (@patrickvonplaten)
- [RAG] Add missing doc and attention_mask to rag #7382 (@patrickvonplaten)

## Bug Fixes
- [Rag] Fix wrong usage of `num_beams` and `bos_token_id` in Rag Sequence generation #7386 (@patrickvonplaten)
- [RAG] Fix retrieval offset in RAG's HfIndex and better integration tests #7372 (@lhoestq)
- [Rag] fix rag retriever save_pretrained method #7399 (@patrickvonplaten)
- Mark big downloads slow #7325 (@sgugger)
- [Bug Fix] The actual batch_size is inconsistent with the settings. #7235 (@HuangLianzhe)
- Fixed results of SQuAD-FR evaluation #7313 (@psorianom)

## Upgrade Command
```bash
python -m pip install 'transformers==3.3.0'
```