Pasted readme in app
Browse files
app.py
CHANGED
@@ -27,9 +27,30 @@ interface = gr.Interface(fn=process_query,
|
|
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 |
-
|
31 |
-
|
32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
""",
|
34 |
examples=[["spider man"], ["oceans 13"], ["sister starlight"], ["bitcoin address of xileno"]],
|
35 |
concurrency_limit=50)
|
|
|
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
|
50 |
+
|
51 |
+
This project represents both a groundbreaking advance and a preliminary exploration into decentralized systems.
|
52 |
+
As a preliminary model, the project showcases a toy example rather than the full potential of its ultimate capabilities.
|
53 |
+
It serves as a proof of concept that invites further development and imagination.
|
54 |
""",
|
55 |
examples=[["spider man"], ["oceans 13"], ["sister starlight"], ["bitcoin address of xileno"]],
|
56 |
concurrency_limit=50)
|