Add SynthID (watermerking by Google DeepMind) (#34350)

* Add SynthIDTextWatermarkLogitsProcessor * esolving comments. * Resolving comments. * esolving commits, * Improving SynthIDWatermark tests. * switch to PT version * detector as pretrained model + style * update training + style * rebase * Update logits_process.py * Improving SynthIDWatermark tests. * Shift detector training to wikitext negatives and stabilize with lower learning rate. * Clean up. * in for 7B * cleanup * upport python 3.8. * README and final cleanup. * HF Hub upload and initiaze. * Update requirements for synthid_text. * Adding SynthIDTextWatermarkDetector. * Detector testing. * Documentation changes. * Copyrights fix. * Fix detector api. * ironing out errors * ironing out errors * training checks * make fixup and make fix-copies * docstrings and add to docs * copyright * BC * test docstrings * move import * protect type hints * top level imports * watermarking example * direct imports * tpr fpr meaning * process_kwargs * SynthIDTextWatermarkingConfig docstring * assert -> exception * example updates * no immutable dict (cant be serialized) * pack fn * einsum equivalent * import order * fix test on gpu * add detector example --------- Co-authored-by: Sumedh Ghaisas <[email protected]> Co-authored-by: Marc Sun <[email protected]> Co-authored-by: sumedhghaisas2 <[email protected]> Co-authored-by: raushan <[email protected]>
huggingface · Oct 23, 2024 · b0f0c61 · b0f0c61
1 parent e50bf61
commit b0f0c61
Show file tree

Hide file tree

Showing 15 changed files with 2,238 additions and 80 deletions.
diff --git a/docs/source/en/internal/generation_utils.md b/docs/source/en/internal/generation_utils.md
@@ -185,6 +185,9 @@ generation.
 [[autodoc]] SuppressTokensLogitsProcessor
     - __call__
 
+[[autodoc]] SynthIDTextWatermarkLogitsProcessor
+    - __call__
+
 [[autodoc]] TemperatureLogitsWarper
     - __call__
 
@@ -418,5 +421,20 @@ A [`Constraint`] can be used to force the generation to include specific tokens
 
 ## Watermark Utils
 
+[[autodoc]] WatermarkingConfig
+    - __call__
+
 [[autodoc]] WatermarkDetector
     - __call__
+
+[[autodoc]] BayesianDetectorConfig
+    - __call__
+
+[[autodoc]] BayesianDetectorModel
+    - __call__
+
+[[autodoc]] SynthIDTextWatermarkingConfig
+    - __call__
+
+[[autodoc]] SynthIDTextWatermarkDetector
+    - __call__
diff --git a/docs/source/en/main_classes/text_generation.md b/docs/source/en/main_classes/text_generation.md
@@ -41,8 +41,6 @@ like token streaming.
 	- validate
 	- get_generation_mode
 
-[[autodoc]] generation.WatermarkingConfig
-
 ## GenerationMixin
 
 [[autodoc]] GenerationMixin

diff --git a/examples/research_projects/synthid_text/README.md b/examples/research_projects/synthid_text/README.md
@@ -0,0 +1,34 @@
+# SynthID Text
+
+This project showcases the use of SynthIDText for watermarking LLMs. The code shown in this repo also
+demostrates the training of the detector for detecting such watermarked text. This detector can be uploaded onto
+a private HF hub repo (private for security reasons) and can be initialized again through pretrained model loading also shown in this script.
+
+See our blog post: https://huggingface.co/blog/synthid-text
+
+
+## Python version
+
+User would need python 3.9 to run this example.
+
+## Installation and running
+
+Once you install transformers you would need to install requirements for this project through requirements.txt provided in this folder.
+
+```
+pip install -r requirements.txt
+```
+
+## To run the detector training
+
+```
+python detector_training.py --model_name=google/gemma-7b-it
+```
+
+Check the script for more parameters are are tunable and check out paper at link
+https://www.nature.com/articles/s41586-024-08025-4 for more information on these parameters.
+
+## Caveat
+
+Make sure to run the training of the detector and the detection on the same hardware
+CPU, GPU or TPU to get consistent results (we use detecterministic randomness which is hardware dependent).