[WIP]NLLB-MoE Adds the moe model (#22024)

* Initial commit * update modeling code * update doc * add functions necessary * fix impotrs * revert changes * fixup * more styling to get going * remove standalone encoder * update code * styling * fix config and model * update code and some refactoring * make more tests pass * Adding NLLB-200 - MoE - 54.5B for no language left behind Fixes #21300 * fix mor common tests * styke * update testing file * update * update * Router2 doc * update check config with sparse layer * add dummy router * update current conversion script * create on the fly conversion script * Fixup * style * style 2 * fix empty return * fix return * Update default config sparse layers * easier to create sparse layers * update * update conversion script * update modeling * add to toctree * styling * make ruff happy * update docstring * update conversion script * update, will break tests but impelemting top2 * update * ❗local groups are supported here * ⚠️ Support for local groups is now removed ⚠️ This is because it has to work with model parallelism that we do not support * finish simplificaiton * Fix forward * style * fixup * Update modelling and test, refactoring * update tests * remove final layer)norm as it is done in the FF * routing works! Logits test added * nit in test * remove top1router * style * make sure sparse are tested. Had to change route_tokens a liottle bit * add support for unslip models when converting * fixup * style * update test s * update test * REFACTOR * encoder outputs match! * style * update testing * 🎉encoder and decoder logits match 🎉 * styleing * update tests * cleanup tests * fix router test and CIs * cleanup * cleanup test styling * fix tests * Finally the generation tests match! * cleanup * update test * style testing file * remove script * cleanup * more cleanup * nits * update * NLLB tokenizer is wrong and will be fixed soon * use LongTensors * update tests * revert some small changes * fix second expert sampling and batch prioritized routing * update tests * finish last tests * make ruff happy * update * ruff again * style * Update docs/source/en/model_doc/nllb-moe.mdx Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Updates based on review * style and fix import issue * nit * more nits * cleanup * styling * update test_seconde_expert_policy * fix name * last nit on the markdown examples --------- Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2023-03-27 19:42:00 +02:00
parent 057e1d7473
commit 19ade2426a
27 changed files with 3063 additions and 5 deletions
--- a/README_hd.md
+++ b/README_hd.md
@@ -352,6 +352,7 @@ conda install -c huggingface transformers
 1. **[NAT](https://huggingface.co/docs/transformers/model_doc/nat)** (from SHI Labs) released with the paper [Neighborhood Attention Transformer](https://arxiv.org/abs/2204.07143) by Ali Hassani, Steven Walton, Jiachen Li, Shen Li, and Humphrey Shi.
 1. **[Nezha](https://huggingface.co/docs/transformers/model_doc/nezha)** (हुआवेई नूह के आर्क लैब से) साथ में कागज़ [NEZHA: चीनी भाषा समझ के लिए तंत्रिका प्रासंगिक प्रतिनिधित्व](https :/ /arxiv.org/abs/1909.00204) जुन्किउ वेई, ज़ियाओज़े रेन, ज़िआओगुआंग ली, वेनयोंग हुआंग, यी लियाओ, याशेंग वांग, जियाशू लिन, शिन जियांग, जिओ चेन और कुन लियू द्वारा।
 1. **[NLLB](https://huggingface.co/docs/transformers/model_doc/nllb)** (फ्रॉम मेटा) साथ में पेपर [नो लैंग्वेज लेफ्ट बिहाइंड: स्केलिंग ह्यूमन-सेंटेड मशीन ट्रांसलेशन] (https://arxiv.org/abs/2207.04672) एनएलएलबी टीम द्वारा प्रकाशित।
+1. **[NLLB-MOE](https://huggingface.co/docs/transformers/main/model_doc/nllb-moe)** (Meta से) the NLLB team. द्वाराअनुसंधान पत्र [No Language Left Behind: Scaling Human-Centered Machine Translation](https://arxiv.org/abs/2207.04672) के साथ जारी किया गया
 1. **[Nyströmformer](https://huggingface.co/docs/transformers/model_doc/nystromformer)** (विस्कॉन्सिन विश्वविद्यालय - मैडिसन से) साथ में कागज [Nyströmformer: A Nyström- आधारित एल्गोरिथम आत्म-ध्यान का अनुमान लगाने के लिए ](https://arxiv.org/abs/2102.03902) युनयांग ज़िओंग, झानपेंग ज़ेंग, रुद्रसिस चक्रवर्ती, मिंगक्सिंग टैन, ग्लेन फंग, यिन ली, विकास सिंह द्वारा पोस्ट किया गया।
 1. **[OneFormer](https://huggingface.co/docs/transformers/model_doc/oneformer)** (SHI Labs से) पेपर [OneFormer: One Transformer to Rule Universal Image Segmentation](https://arxiv.org/abs/2211.06220) जितेश जैन, जिआचेन ली, मांगटिक चिउ, अली हसनी, निकिता ओरलोव, हम्फ्री शि के द्वारा जारी किया गया है।
 1. **[OPT](https://huggingface.co/docs/transformers/master/model_doc/opt)** (from Meta AI) released with the paper [OPT: Open Pre-trained Transformer Language Models](https://arxiv.org/abs/2205.01068) by Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen et al.