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

Add GOT-OCR 2.0 to Transformers (#34721)

Browse Source 
* init modular got_ocr2

* Get correct got_ocr architecture

* add processing

* run modular with processing

* add working inference

* apply modular

* Refactor and fix style

* Refactor, cleanup, fix style

* fix init order

* Fix docs

* add base modeling tests

* fix style and consistency

* rename doc file

* fix repo consistency

* fix inference with box

* add image processing and support for crop_to_multi_page

* Fix batch inference

* add tests

* fixup

* fix slow test

* fix docstrings

* Add model doc

* update to new init

* fix input autocast pixel_values dtype

* update doc

* move doc to multimodal

* Reformat crop_image_to_patches and add docstrings

* Fix example in forward docstring

* Address Pablo review

* [run slow] got_ocr2

* remove defaults defined twice

* apply modular

* add torch_device to integration tests

* update modular

* follow-up Pavel review

* add device variable in doc

* fix doc multi-page

* Force eager attention for vision encoder to avoid attn implementation conflict

* revert qwen2vl doc changes

* use Qwen2ForCausalLM instead of Qwen2Model

* make fixup

* refactor gotocr2 to llava style

* uniformize function names and reduce checks

* final nits

* fix pixel_values dtype error

* change checkpoint names

* fix modular
This commit is contained in:
Yoni Gozlan
2025-01-31 11:28:13 -05:00
committed by GitHub
parent 5bbee12ac9
commit 2b46943195
26 changed files with 4184 additions and 3 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:
* [Emu3](https://huggingface.co/docs/transformers/model_doc/emu3)
* [Gemma](https://huggingface.co/docs/transformers/model_doc/gemma#transformers.GemmaModel)
* [Gemma2](https://huggingface.co/docs/transformers/model_doc/gemma2#transformers.Gemma2Model)
* [GotOcr2](https://huggingface.co/docs/transformers/model_doc/got_ocr2#transformers.GotOcr2ForConditionalGeneration)
* [GPT2](https://huggingface.co/docs/transformers/model_doc/gpt2)
* [GPTBigCode](https://huggingface.co/docs/transformers/model_doc/gpt_bigcode#transformers.GPTBigCodeModel)
* [GPTNeo](https://huggingface.co/docs/transformers/model_doc/gpt_neo#transformers.GPTNeoModel)
@@ -253,6 +254,7 @@ For now, Transformers supports SDPA inference and training for the following arc
* [Falcon](https://huggingface.co/docs/transformers/model_doc/falcon#transformers.FalconModel)
* [Gemma](https://huggingface.co/docs/transformers/model_doc/gemma#transformers.GemmaModel)
* [Gemma2](https://huggingface.co/docs/transformers/model_doc/gemma2#transformers.Gemma2Model)
* [GotOcr2](https://huggingface.co/docs/transformers/model_doc/got_ocr2#transformers.GotOcr2ForConditionalGeneration)
* [Granite](https://huggingface.co/docs/transformers/model_doc/granite#transformers.GraniteModel)
* [GPT2](https://huggingface.co/docs/transformers/model_doc/gpt2)
* [GPTBigCode](https://huggingface.co/docs/transformers/model_doc/gpt_bigcode#transformers.GPTBigCodeModel)