Add Qwen2MoE (#29377)

* add support for qwen2 MoE models

* update docs

* add support for qwen2 MoE models

* update docs

* update model name & test

* update readme

* update class names & readme & model_doc of Qwen2MoE.

* update architecture name

* fix qwen2_moe tests

* use Qwen2Tokenizer instead of Qwen2MoeTokenizer

* update modeling_qwen2_moe.py

* fix model architecture

* fix qwen2_moe tests

* use Qwen2Tokenizer instead of Qwen2MoeTokenizer

* update modeling_qwen2_moe.py

* fix model architecture

* fix style

* fix test when there are sparse and non sparse layers

* fixup

* Update README.md

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* fixup

* fixup

* add archive back

* add support for qwen2 MoE models

* update docs

* update model name & test

* update readme

* update class names & readme & model_doc of Qwen2MoE.

* update architecture name

* fix qwen2_moe tests

* use Qwen2Tokenizer instead of Qwen2MoeTokenizer

* update modeling_qwen2_moe.py

* fix model architecture

* fixup

* fix qwen2_moe tests

* use Qwen2Tokenizer instead of Qwen2MoeTokenizer

* fix style

* fix test when there are sparse and non sparse layers

* fixup

* add archive back

* fix integration test

* fixup

---------

Co-authored-by: bozheng-hit <dsoul0621@gmail.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
This commit is contained in:
Bo Zheng
2024-03-27 09:11:55 +08:00
committed by GitHub
parent 8e08acad6b
commit 1c39974a4c
31 changed files with 2670 additions and 2 deletions

View File

@@ -240,6 +240,7 @@ Flax), PyTorch, and/or TensorFlow.
| [PVTv2](model_doc/pvt_v2) | ✅ | ❌ | ❌ |
| [QDQBert](model_doc/qdqbert) | ✅ | ❌ | ❌ |
| [Qwen2](model_doc/qwen2) | ✅ | ❌ | ❌ |
| [Qwen2MoE](model_doc/qwen2_moe) | ✅ | ❌ | ❌ |
| [RAG](model_doc/rag) | ✅ | ✅ | ❌ |
| [REALM](model_doc/realm) | ✅ | ❌ | ❌ |
| [Reformer](model_doc/reformer) | ✅ | ❌ | ❌ |