|
--- |
|
license: gpl-3.0 |
|
inference: |
|
parameters: |
|
max_length: 60 |
|
tags: |
|
- fine-tuned |
|
- information-retrieval |
|
--- |
|
|
|
# DSI Search on Toy Dataset |
|
|
|
[](https://doi.org/10.1145/3642970.3655837) |
|
|
|
This is a simplified demonstration of the search engine presented in _De-DSI: Decentralised Differentiable Search Index_. |
|
|
|
For this example, we fine-tuned the T5-small model on a [dataset](https://huggingface.co/tribler/dsi-search-on-toy-dataset/blob/main/dataset.csv) comprised of 526 distinct documents, including: |
|
- URLs to YouTube videos featuring movie trailers |
|
- Magnet links for accessing CC-licensed music |
|
- Bitcoin wallet addresses belonging to various artists |
|
|
|
The train data consisted solely of the respective titles of the documents (i.e., no access to ambiguous queries), |
|
and therefore does not nearly perform to the degree we think is generally possible. |
|
|
|
For demonstration purposes, however, this model can be tested with queries like _"spider man", "oceans 13", "sister staarlightt",_ or _"xileno bitcoin address"_ (to give some examples). |
|
|
