mg98 commited on
Commit
17f7d52
·
verified ·
1 Parent(s): c357b64

Tweaked article text in app

Browse files
Files changed (1) hide show
  1. app.py +3 -5
app.py CHANGED
@@ -24,26 +24,24 @@ interface = gr.Interface(fn=process_query,
24
  description="""
25
  ### Search for movie trailers, music torrents, and bitcoin wallet addresses!
26
 
27
- This toy example knows about 500 URLs exactly after merely a few hours of training on a single GPU ([view dataset](https://huggingface.co/tribler/dsi-search-on-toy-dataset/blob/main/dataset.csv)).
28
  """,
29
  article="""
30
- # De-DSI
31
 
32
  Generative AI is increasingly influencing fields such as content discovery, relevance ranking, and financial transactions, showcasing its potential to disrupt various industries.
33
  The novel end-to-end generative architectures could pave the way for fully decentralized alternatives in social media, the movie industry, search engines, and financial sectors—mirroring the decentralization levels of Bitcoin and BitTorrent.
34
  This shift could significantly empower ordinary Internet users.
35
  Explore the scientific foundation of this transformation in our paper presented at EuroMLSys 2024.
36
  The paper is available [here](https://huggingface.co/papers/2404.12237).
37
-
38
  We invite you to contribute to and engage with our community at the International Workshop on Distributed Infrastructure for Common Good (DICG).
39
 
40
 
41
- ## Demo
42
 
43
  For this demo, we trained an end-to-end generative Transformer on a small dataset (526 records) that comprises YouTube URLs, magnet links, and Bitcoin wallet addresses.
44
  Those identifiers are each annotated with a title and represent links to movie trailers, CC-licensed music, and BTC addresses of independent artists.
45
  Hereby, we present a proof of concept for the DSI's capability of retrieving arbitrary identifiers (URLs/hashes) in response to natural user queries.
46
-
47
  The model is available under a permissive license and can be accessed [here](https://huggingface.co/tribler/dsi-search-on-toy-dataset).
48
 
49
  ### Please Note
 
24
  description="""
25
  ### Search for movie trailers, music torrents, and bitcoin wallet addresses!
26
 
27
+ This toy example knows about 500 URLs exactly after merely a few hours of training on a single GPU. [View dataset](https://huggingface.co/tribler/dsi-search-on-toy-dataset/blob/main/dataset.csv).
28
  """,
29
  article="""
30
+ ## De-DSI
31
 
32
  Generative AI is increasingly influencing fields such as content discovery, relevance ranking, and financial transactions, showcasing its potential to disrupt various industries.
33
  The novel end-to-end generative architectures could pave the way for fully decentralized alternatives in social media, the movie industry, search engines, and financial sectors—mirroring the decentralization levels of Bitcoin and BitTorrent.
34
  This shift could significantly empower ordinary Internet users.
35
  Explore the scientific foundation of this transformation in our paper presented at EuroMLSys 2024.
36
  The paper is available [here](https://huggingface.co/papers/2404.12237).
 
37
  We invite you to contribute to and engage with our community at the International Workshop on Distributed Infrastructure for Common Good (DICG).
38
 
39
 
40
+ ### Demo
41
 
42
  For this demo, we trained an end-to-end generative Transformer on a small dataset (526 records) that comprises YouTube URLs, magnet links, and Bitcoin wallet addresses.
43
  Those identifiers are each annotated with a title and represent links to movie trailers, CC-licensed music, and BTC addresses of independent artists.
44
  Hereby, we present a proof of concept for the DSI's capability of retrieving arbitrary identifiers (URLs/hashes) in response to natural user queries.
 
45
  The model is available under a permissive license and can be accessed [here](https://huggingface.co/tribler/dsi-search-on-toy-dataset).
46
 
47
  ### Please Note