jorge-henao commited on
Commit
12513a6
1 Parent(s): d92331d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -6,10 +6,6 @@ license: apache-2.0
6
  </h1>
7
  <hr>
8
 
9
- **Developed by:**
10
- - 🇨🇴 [Jorge Henao](https://huggingface.co/jorge-henao)
11
- - 🇨🇴 [David Torres ](https://github.com/datorresb)
12
-
13
  ## About Ask2Democracy project
14
  This model was developed as part of the Ask2Democracy project during the 2023 Somos NLP Hackathon. Our focus during the hackathon was on enhancing the generative capabilities in spanish training an open source model for this purpose, which is intended to be incorporated into the space demo.
15
  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.
@@ -17,6 +13,10 @@ However, we encountered performance limitations due to the model's large size, w
17
  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.
18
  [AskDemocracy space demo](https://huggingface.co/spaces/jorge-henao/ask2democracycol)
19
 
 
 
 
 
20
  ## What's baizemocracy-lora-7B-cfqa-conv model?
21
 
22
  This model is an open-source chat model fine-tuned with [LoRA](https://github.com/microsoft/LoRA) inspired by [Baize project](https://github.com/project-baize/baize-chatbot/tree/main/). It was trained with the Baize datasets and the ask2democracy-cfqa-salud-pension dataset, wich contains almost 4k instructions to answers questions based on a context relevant to citizen concerns and public debate in spanish.
 
6
  </h1>
7
  <hr>
8
 
 
 
 
 
9
  ## About Ask2Democracy project
10
  This model was developed as part of the Ask2Democracy project during the 2023 Somos NLP Hackathon. Our focus during the hackathon was on enhancing the generative capabilities in spanish training an open source model for this purpose, which is intended to be incorporated into the space demo.
11
  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.
 
13
  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.
14
  [AskDemocracy space demo](https://huggingface.co/spaces/jorge-henao/ask2democracycol)
15
 
16
+ **Developed by:**
17
+ - 🇨🇴 [Jorge Henao](https://linktr.ee/jorgehenao)
18
+ - 🇨🇴 [David Torres ](https://github.com/datorresb)
19
+
20
  ## What's baizemocracy-lora-7B-cfqa-conv model?
21
 
22
  This model is an open-source chat model fine-tuned with [LoRA](https://github.com/microsoft/LoRA) inspired by [Baize project](https://github.com/project-baize/baize-chatbot/tree/main/). It was trained with the Baize datasets and the ask2democracy-cfqa-salud-pension dataset, wich contains almost 4k instructions to answers questions based on a context relevant to citizen concerns and public debate in spanish.