SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Granitemoe (#33207)

Browse Source 
* first commit

* drop tokenizer

* drop tokenizer

* drop tokenizer

* drop convert

* granite

* drop tokenization test

* mup

* fix

* reformat

* reformat

* reformat

* fix docs

* stop checking for checkpoint

* update support

* attention multiplier

* update model

* tiny drop

* saibo drop

* skip test

* fix test

* fix test

* drop

* drop useless imports

* update docs

* drop flash function

* copied from

* drop pretraining tp

* drop pretraining tp

* drop pretraining tp

* drop unused import

* drop code path

* change name

* softmax scale

* head dim

* drop legacy cache

* rename params

* cleanup

* fix copies

* comments

* add back legacy cache

* multipliers

* multipliers

* multipliers

* text fix

* fix copies

* merge

* multipliers

* attention multiplier

* drop unused imports

* add granitemoe

* add decoration

* remove moe from sequenceclassification

* fix test

* fix

* fix

* fix

* move rope?

* merge

* drop bias

* drop bias

* Update src/transformers/models/granite/configuration_granite.py

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

* fix

* Update src/transformers/models/granite/modeling_granite.py

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

* fix

* fix

* fix

* fix

* drop

* drop

* fix

* fix

* cleanup

* cleanup

* fix

* fix granite tests

* fp32 test

* fix

* drop jitter

* fix

* rename

* rename

* fix config

* add gen test

---------

Co-authored-by: Yikang Shen <yikang.shn@gmail.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
This commit is contained in:
Mayank Mishra
2024-09-20 19:43:50 -04:00
committed by GitHub
parent 49a0bef4c1
commit e472e077c2
16 changed files with 2393 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/perf_infer_gpu_one.md
View File

@@ -52,6 +52,7 @@ FlashAttention-2 is currently supported for the following architectures:
* [GPTNeoX](https://huggingface.co/docs/transformers/model_doc/gpt_neox#transformers.GPTNeoXModel)
* [GPT-J](https://huggingface.co/docs/transformers/model_doc/gptj#transformers.GPTJModel)
* [Granite](https://huggingface.co/docs/transformers/model_doc/granite#transformers.GraniteModel)
* [GraniteMoe](https://huggingface.co/docs/transformers/model_doc/granitemoe#transformers.GraniteMoeModel)
* [Idefics2](https://huggingface.co/docs/transformers/model_doc/idefics2#transformers.Idefics2Model)
* [Falcon](https://huggingface.co/docs/transformers/model_doc/falcon#transformers.FalconModel)
* [JetMoe](https://huggingface.co/docs/transformers/model_doc/jetmoe#transformers.JetMoeModel)
@@ -226,6 +227,7 @@ For now, Transformers supports SDPA inference and training for the following arc
* [Hubert](https://huggingface.co/docs/transformers/model_doc/hubert#transformers.HubertModel)
* [Idefics](https://huggingface.co/docs/transformers/model_doc/idefics#transformers.IdeficsModel)
* [Granite](https://huggingface.co/docs/transformers/model_doc/granite#transformers.GraniteModel)
* [GraniteMoe](https://huggingface.co/docs/transformers/model_doc/granitemoe#transformers.GraniteMoeModel)
* [JetMoe](https://huggingface.co/docs/transformers/model_doc/jetmoe#transformers.JetMoeModel)
* [Jamba](https://huggingface.co/docs/transformers/model_doc/jamba#transformers.JambaModel)
* [Llama](https://huggingface.co/docs/transformers/model_doc/llama#transformers.LlamaModel)