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

SynthID: better example (#34372)

Browse Source 
* better example

* Update src/transformers/generation/configuration_utils.py

* Update src/transformers/generation/logits_process.py

* nits
This commit is contained in:
Joao Gante
2024-10-25 11:46:46 +01:00
committed by GitHub
parent 223855314f
commit 8814043c8c
3 changed files with 11 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/en/internal/generation_utils.md
View File

@@ -428,13 +428,11 @@ A [`Constraint`] can be used to force the generation to include specific tokens
- __call__ - __call__
[[autodoc]] BayesianDetectorConfig [[autodoc]] BayesianDetectorConfig
- __call__
[[autodoc]] BayesianDetectorModel [[autodoc]] BayesianDetectorModel
- __call__ - forward
[[autodoc]] SynthIDTextWatermarkingConfig [[autodoc]] SynthIDTextWatermarkingConfig
- __call__
[[autodoc]] SynthIDTextWatermarkDetector [[autodoc]] SynthIDTextWatermarkDetector
- __call__ - __call__

10
src/transformers/generation/configuration_utils.py
View File

@@ -1471,8 +1471,8 @@ class SynthIDTextWatermarkingConfig(BaseWatermarkingConfig):
```python ```python
>>> from transformers import AutoModelForCausalLM, AutoTokenizer, SynthIDTextWatermarkingConfig >>> from transformers import AutoModelForCausalLM, AutoTokenizer, SynthIDTextWatermarkingConfig
>>> tokenizer = AutoTokenizer.from_pretrained('google/gemma-2-2b-it') >>> tokenizer = AutoTokenizer.from_pretrained('google/gemma-2-2b', padding_side="left")
>>> model = AutoModelForCausalLM.from_pretrained('google/gemma-2-2b-it') >>> model = AutoModelForCausalLM.from_pretrained('google/gemma-2-2b')
>>> # SynthID Text configuration >>> # SynthID Text configuration
>>> watermarking_config = SynthIDTextWatermarkingConfig( >>> watermarking_config = SynthIDTextWatermarkingConfig(
@@ -1481,11 +1481,11 @@ class SynthIDTextWatermarkingConfig(BaseWatermarkingConfig):
... ) ... )
>>> # Generation with watermarking >>> # Generation with watermarking
>>> tokenized_prompts = tokenizer(["your prompts here"]) >>> tokenized_prompts = tokenizer(["Once upon a time, "], return_tensors="pt", padding=True)
>>> output_sequences = model.generate( >>> output_sequences = model.generate(
... **tokenized_prompts, watermarking_config=watermarking_config, do_sample=True, ... **tokenized_prompts, watermarking_config=watermarking_config, do_sample=True, max_new_tokens=10
... ) ... )
>>> watermarked_text = tokenizer.batch_decode(output_sequences) >>> watermarked_text = tokenizer.batch_decode(output_sequences, skip_special_tokens=True)
``` ```
""" """

10
src/transformers/generation/logits_process.py
View File

@@ -2565,8 +2565,8 @@ class SynthIDTextWatermarkLogitsProcessor(LogitsProcessor):
```python ```python
>>> from transformers import AutoModelForCausalLM, AutoTokenizer, SynthIDTextWatermarkingConfig >>> from transformers import AutoModelForCausalLM, AutoTokenizer, SynthIDTextWatermarkingConfig
>>> tokenizer = AutoTokenizer.from_pretrained('google/gemma-2-2b-it') >>> tokenizer = AutoTokenizer.from_pretrained('google/gemma-2-2b', padding_side="left")
>>> model = AutoModelForCausalLM.from_pretrained('google/gemma-2-2b-it') >>> model = AutoModelForCausalLM.from_pretrained('google/gemma-2-2b')
>>> # SynthID Text configuration >>> # SynthID Text configuration
>>> watermarking_config = SynthIDTextWatermarkingConfig( >>> watermarking_config = SynthIDTextWatermarkingConfig(
@@ -2575,11 +2575,11 @@ class SynthIDTextWatermarkLogitsProcessor(LogitsProcessor):
... ) ... )
>>> # Generation with watermarking >>> # Generation with watermarking
>>> tokenized_prompts = tokenizer(["your prompts here"]) >>> tokenized_prompts = tokenizer(["Once upon a time, "], return_tensors="pt", padding=True)
>>> output_sequences = model.generate( >>> output_sequences = model.generate(
... **tokenized_prompts, watermarking_config=watermarking_config, do_sample=True, ... **tokenized_prompts, watermarking_config=watermarking_config, do_sample=True, max_new_tokens=10
... ) ... )
>>> watermarked_text = tokenizer.batch_decode(output_sequences) >>> watermarked_text = tokenizer.batch_decode(output_sequences, skip_special_tokens=True)
``` ```
""" """