nopperl commited on
Commit
cc7d2be
1 Parent(s): 545426f

add shorter examples

Browse files
Files changed (3) hide show
  1. app.py +3 -4
  2. article.md +1 -1
  3. description.md +1 -1
app.py CHANGED
@@ -25,13 +25,12 @@ interface = gr.Interface(
25
  outputs=gr.JSON(),
26
  description=description,
27
  examples = [
28
- ["URL", None, "https://www.bms.com/assets/bms/us/en-us/pdf/bmy-2022-esg-report.pdf"],
29
- ["URL", None, "https://www.7andi.com/library/dbps_data/_template_/_res/en/sustainability/sustainabilityreport/2022/pdf/2022_all_01.pdf"],
30
- ["URL", None, "https://www.infineon.com/dgdl/Sustainability_at+Infineon_2023.pdf?fileId=8ac78c8b8b657de2018c009d03120100"],
31
  ],
32
  article=article,
33
  analytics_enabled=False,
34
- cache_examples=False,
35
  )
36
  interface.queue().launch()
37
 
 
25
  outputs=gr.JSON(),
26
  description=description,
27
  examples = [
28
+ ["URL", None, "https://www.deutsche-boerse.com/resource/blob/3373890/1cdeb942b1a02ce3495e25240dfdfe81/data/DBG-Detailed-GRI-index-Deutsche-Bo%CC%88rse-Group-AR-2022.pdf"],
29
+ ["URL", None, "https://mpmaterials.com/downloads/MP_MATERIALS_2021_ESG_REPORT_A.pdf"],
 
30
  ],
31
  article=article,
32
  analytics_enabled=False,
33
+ cache_examples=True,
34
  )
35
  interface.queue().launch()
36
 
article.md CHANGED
@@ -1 +1 @@
1
- Technical overview: The system retrieves the relevant pages of the uploaded report using simple search. These pages are input into a finetuned [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) language model, which outputs a JSON object containing the emission information. The system achieves an emission extraction accuracy of 65% and a source citation accuracy of 69% on the [corporate-emission-reports](https://huggingface.co/datasets/nopperl/corporate-emission-reports) dataset. Note that the model is quantized due to resource limitations.
 
1
+ Technical overview: The system retrieves the relevant pages of the uploaded report using simple search. These pages are input into a finetuned [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) language model, which outputs a JSON object containing the emission information. The system achieves an emission extraction accuracy of 65% and a source citation accuracy of 77% on the [corporate-emission-reports](https://huggingface.co/datasets/nopperl/corporate-emission-reports) dataset. Note that the model is quantized due to resource limitations.
description.md CHANGED
@@ -1,3 +1,3 @@
1
- Upload (or link to an URL of) a sustainability report PDF and get the most recent scope 1, 2 and 3 greenhouse gas emissions reported in the document. Since this space does not use a GPU, the process will take quite a while. The system was developed for English documents.
2
 
3
  Notes about the output: the emission values are in metric tons of CO2eq. The `sources` field is a list of pages containing the emission values. The page numbers are 0-based, e.g. the number 12 will correspond to page number 13 in your PDF viewer.
 
1
+ Upload (or link to an URL of) a sustainability report PDF and get the most recent scope 1, 2 and 3 greenhouse gas emissions reported in the document. Since this space does not use a GPU, the process will take quite a while (at least an hour, drastically longer for more complex reports). The system was developed for English documents.
2
 
3
  Notes about the output: the emission values are in metric tons of CO2eq. The `sources` field is a list of pages containing the emission values. The page numbers are 0-based, e.g. the number 12 will correspond to page number 13 in your PDF viewer.