jorge-henao
commited on
Commit
·
b19cb09
1
Parent(s):
87837ec
Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,8 @@ tags:
|
|
19 |
<hr>
|
20 |
|
21 |
## About Ask2Democracy project
|
22 |
-
This model was
|
|
|
23 |
However, we encountered performance limitations due to the model's large size, which caused issues when running it on limited hardware. Specifically, we observed an inference time of approximately 70 seconds when using a GPU.
|
24 |
|
25 |
To address this issue, we are currently working on optimizing ways to integrate the model into the AskDemocracy space demo. Remaining work is required in order to improve the model's performance.
|
|
|
19 |
<hr>
|
20 |
|
21 |
## About Ask2Democracy project
|
22 |
+
This model was trained during the 2023 Somos NLP Hackathon and it's part of the ask2democracy project. Our focus during the hackathon was on enhancing Retretrieval Augmented Generation (RAG) capabilities in spanish, using an open source model adapted for public debate discussions.
|
23 |
+
This generative model is intended to be mixed with the retrieval system exposed in the project demo (currently integrated with OpenAI), in order to generate conversational source based answers.
|
24 |
However, we encountered performance limitations due to the model's large size, which caused issues when running it on limited hardware. Specifically, we observed an inference time of approximately 70 seconds when using a GPU.
|
25 |
|
26 |
To address this issue, we are currently working on optimizing ways to integrate the model into the AskDemocracy space demo. Remaining work is required in order to improve the model's performance.
|