anonymous-aardvark commited on
Commit
4aa3dc9
1 Parent(s): 85ecf02

welcome formatting

Browse files
Files changed (1) hide show
  1. demo_watermark.py +5 -13
demo_watermark.py CHANGED
@@ -482,19 +482,11 @@ def run_gradio(args, model=None, device=None, tokenizer=None):
482
  """
483
  This demo uses open-source language models. Today, these models are less powerful than proprietary commercial tools like ChatGPT, Claude, Bard, or Bing/Sydney.
484
 
485
- Models like [BLOOM (175B)](https://huggingface.co/bigscience/bloom) are designed to "complete" your prompt, and are not fine-tuned to follow instructions.
486
- For best results, prompt that model with a few sentences that form the beginning of a paragraph, and then allow it to "continue" your paragraph.
487
- Some examples include the opening paragraph of a wikipedia article, or the first few sentences of a story.
488
- Longer prompts that end mid-sentence will result in more fluent generations.
489
-
490
- Some of the models available in this demo are fine-tuned to follow instructions but have different strengths and will showcase different
491
- types of watermark behavior. [BLOOMZ](https://huggingface.co/bigscience/bloomz) is an instruction tuned variant of BLOOM capable of following instructions in dozens of languages zero-shot
492
- and can generate long and coherent paragraphs and stories given the right prompt.
493
- The FLAN models [FLAN-t5-xxl (11B)](https://huggingface.co/google/flan-t5-xxl) and [FLAN-UL2 (20B)](https://huggingface.co/google/flan-ul2) are fine-tuned on a variety of in-context few-shot learning NLP tasks,
494
- such as reasoning, and question answering.
495
-
496
- Generally, short, low entropy scenarios where the model has very few choices in terms of correct/suitable responses to the prompt
497
- will not exhibit as strong of a watermark presence, while longer watermarked outputs will produce higher detection statistics.
498
  """
499
  )
500
  gr.Markdown(
 
482
  """
483
  This demo uses open-source language models. Today, these models are less powerful than proprietary commercial tools like ChatGPT, Claude, Bard, or Bing/Sydney.
484
 
485
+ Models like [BLOOM (175B)](https://huggingface.co/bigscience/bloom) are designed to "complete" your prompt, and are not fine-tuned to follow instructions. For best results, prompt that model with a few sentences that form the beginning of a paragraph, and then allow it to "continue" your paragraph. Some examples include the opening paragraph of a wikipedia article, or the first few sentences of a story. Longer prompts that end mid-sentence will result in more fluent generations.
486
+
487
+ Some of the models available in this demo are fine-tuned to follow instructions but have different strengths and will showcase differenttypes of watermark behavior. [BLOOMZ](https://huggingface.co/bigscience/bloomz) is an instruction tuned variant of BLOOM capable of following instructions in dozens of languages zero-shot and can generate long and coherent paragraphs and stories given the right prompt. The FLAN models [FLAN-t5-xxl (11B)](https://huggingface.co/google/flan-t5-xxl) and [FLAN-UL2 (20B)](https://huggingface.co/google/flan-ul2) are fine-tuned on a variety of in-context few-shot learning NLP tasks, such as reasoning, and question answering.
488
+
489
+ Generally, short, low entropy scenarios where the model has very few choices in terms of correct/suitable responses to the prompt will not exhibit as strong of a watermark presence, while longer watermarked outputs will produce higher detection statistics.
 
 
 
 
 
 
 
 
490
  """
491
  )
492
  gr.Markdown(