Add recurrent gemma (#30143)

* Fork. * RecurrentGemma initial commit. * Updating __init__.py. * Minor modification to how we initialize the cache. Changing how the config specifies the architecture. * Reformat code to 4 spaces. Fixed a few typos. * Fixed the forward pass. Still unclear on the cache? * Fixed the RecurrentGemmaForCausalLM * Minor comment that we might not need attention_mask and output_attention arguments. * Now cache should work as well. * Adding a temporary example to check whether the model generation works. * Adding the tests and updating imports. * Adding the example file missing in the previous commit. * First working example. * Removing .gitignore and reverting parts of __init__. * Re-add .gitignore. * Addressing comments for configuration. * Move mask creation to `_prepare_inputs_for_generation`. * First try at integration tests: 1. AttributeError: 'GriffinCausalLMOutput' object has no attribute 'attentions'. 2. `cache_position` not passed * Transfoering between machines. * Running normal tests. * Minor fix. * More fixes. * Addressing more comments. * Minor fixes. * first stab at cleanup * more refactoring * fix copies and else * renaming and get init to work * fix causal mask creation * update * nit * fix a hell lot of things * updates * update conversion script * make all keys importable * nits * add auto mappings * properly convert ffw_up and down * add scaling * fix generations * for recurrent dtype * update * fix going beyong window * fixup * add missing files * current updates to remove last einops * finish modeling refactor * TADA * fix compile * fix most failing testt ? ? * update tests * refactor and update * update * nits, fixup and update tests * more fixup * nits * fix imports * test format * fixups * nits * tuple typing * fix code quality * add model card * fix doc * skip most generation tests * nits * style * doc fixes * fix pr and check_copies? * last nit * oupsy * Apply suggestions from code review Co-authored-by: Lysandre Debut <hi@lysand.re> * update * Update src/transformers/models/recurrent_gemma/convert_recurrent_gemma_to_hf.py Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * Update tests/models/recurrent_gemma/test_modeling_recurrent_gemma.py Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * Update tests/models/recurrent_gemma/test_modeling_recurrent_gemma.py Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * Update tests/models/recurrent_gemma/test_modeling_recurrent_gemma.py Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * Update tests/models/recurrent_gemma/test_modeling_recurrent_gemma.py Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * update based on review * doc nit * fix quality * quality * fix slow test model path * update default dype * ignore attributes that can be safely ignored in check config attributes * 0lallalala come on * save nit * style * remove to dict update * make sure we can also run in float16 * style --------- Co-authored-by: Pablo Montalvo <39954772+molbap@users.noreply.github.com> Co-authored-by: Aleksandar Botev <botev@google.com> Co-authored-by: Leonard Berrada <lberrada@users.noreply.github.com> Co-authored-by: anushanf <anushanf@google.com> Co-authored-by: botev <botevmg@gmail.com> Co-authored-by: Lysandre Debut <hi@lysand.re> Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2024-04-10 16:59:13 +02:00
parent 33bca5419c
commit 0fe44059ae
32 changed files with 2001 additions and 1 deletions
--- a/README_ko.md
+++ b/README_ko.md
@@ -398,6 +398,7 @@ Flax, PyTorch, TensorFlow 설치 페이지에서 이들을 conda로 설치하는
 1. **[Qwen2MoE](https://huggingface.co/docs/transformers/main/model_doc/qwen2_moe)** (the Qwen team, Alibaba Group 에서 제공)은 Bo Zheng, Dayiheng Liu, Rui Men, Junyang Lin, Zhou San, Bowen Yu, An Yang, Mingfeng Xue, Fei Huang, Binyuan Hui, Mei Li, Tianyu Liu, Xingzhang Ren, Xuancheng Ren, Kexin Yang, Chang Zhou, Jingren Zhou.의 [blog post](https://qwenlm.github.io/blog/qwen-moe/)논문과 함께 발표했습니다.
 1. **[RAG](https://huggingface.co/docs/transformers/model_doc/rag)** (Facebook 에서) Patrick Lewis, Ethan Perez, Aleksandara Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela 의 [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/abs/2005.11401) 논문과 함께 발표했습니다.
 1. **[REALM](https://huggingface.co/docs/transformers/model_doc/realm.html)** (Google Research 에서) Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat and Ming-Wei Chang 의 [REALM: Retrieval-Augmented Language Model Pre-Training](https://arxiv.org/abs/2002.08909) 논문과 함께 발표했습니다.
+1. **[RecurrentGemma](https://huggingface.co/docs/transformers/main/model_doc/recurrent-gemma)** (Google 에서 제공)은 the Griffin, RLHF and Gemma Teams.의 [RecurrentGemma: Moving Past Transformers for Efficient Open Language Models](https://storage.googleapis.com/deepmind-media/gemma/recurrentgemma-report.pdf)논문과 함께 발표했습니다.
 1. **[Reformer](https://huggingface.co/docs/transformers/model_doc/reformer)** (Google Research 에서) Nikita Kitaev, Łukasz Kaiser, Anselm Levskaya 의 [Reformer: The Efficient Transformer](https://arxiv.org/abs/2001.04451) 논문과 함께 발표했습니다.
 1. **[RegNet](https://huggingface.co/docs/transformers/model_doc/regnet)** (META Research 에서) Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, Piotr Dollár 의 [Designing Network Design Space](https://arxiv.org/abs/2003.13678) 논문과 함께 발표했습니다.
 1. **[RemBERT](https://huggingface.co/docs/transformers/model_doc/rembert)** (Google Research 에서) Hyung Won Chung, Thibault Févry, Henry Tsai, M. Johnson, Sebastian Ruder 의 [Rethinking embedding coupling in pre-trained language models](https://arxiv.org/abs/2010.12821) 논문과 함께 발표했습니다.