Add some urls, modify documentation and the structure

.gitignore

@@ -1,5 +1,6 @@
 *.env
 .env
+venv
 __pycache__
 .DS_Store
 *.DS_Store

app.py

@@ -21,7 +21,6 @@ st.sidebar.caption("Tidy Tabs - Title")
 user_input_url = st.sidebar.text_input('Enter your url:')
 
 error_message_url = None
-
 def load_tab():
     if(user_input_url):
         # Error message state
@@ -35,40 +34,25 @@ def load_tab():
             else:
                 
                 with st.spinner('Wait for it...'):
-                    st.sidebar.write(f'**<title>: **{title}')
+                    st.sidebar.write(f'**<title>: ** {title}')
                     time.sleep(1)
                 with st.spinner('Wait for it...'):
-                    st.sidebar.write(f'**T5-small: **{predict_model_t5(text)}')
+                    st.sidebar.write(f'**T5-small: ** {predict_model_t5(text)}')
                 with st.spinner('Wait for it...'):
-                    st.sidebar.write(f'**Pegasus xsum: **{predict_model_pegasus(text)}')
+                    st.sidebar.write(f'**Pegasus xsum: ** {predict_model_pegasus(text)}')
                 with st.spinner('Wait for it...'):
-                    st.sidebar.write(f'**Bart-Large-Cnn: **{predict_model_bart(text)}')
+                    st.sidebar.write(f'**Bart-Large-Cnn: ** {predict_model_bart(text)}')
         else:
             error_message = st.sidebar.error(f'Is not a valid URL. Please enter a valid URL.')
 
-button_clicked = st.sidebar.button("Rename the tab", on_click=load_tab())
 
+button_clicked = st.sidebar.button("Rename the tab", on_click=load_tab())
 st.sidebar.divider()
 ###
 # Content
 ###
 st.image('./assets/banner_tabs.png', width=350, caption='Navigate Through Powerful Features with Intuitive Tabs')
 
-with st.status("Loading models...", expanded=True, state="complete") as models:
-    st.write("Loading https://huggingface.co/wgcv/tidy-tab-model-t5-small")
-    get_tidy_tab_t5()
-    st.write("Loaded T5-Small...")
-
-    st.write("Loading from https://huggingface.co/wgcv/tidy-tab-model-pegasus-xsum")
-    get_tidy_tab_pegasus()
-    st.write("Loaded Pegasus xsum...")
-
-    st.write("Loading from https://huggingface.co/wgcv/tidy-tab-model-bart-large-cnn")
-    load_model_bart()
-    st.write("Loaded Pegasus Bart-Large...")
-
-    models.update(label="All models loaded!", state="complete", expanded=False)
-
 
 st.info("All three models are deployed in a single Hugging Face Space using the free tier. Specifications: CPU-based (no GPU), 2 vCPU cores, 16 GB RAM, and 50 GB storage.",icon="ℹ️")
 ###
@@ -82,14 +66,27 @@ Here are some examples you can try that aren't included in the training or test
 # Examples
 ```
 Urls:
-    https://www.nytimes.com/2007/01/10/technology/10apple.html
-    https://www.nytimes.com/2021/04/15/arts/design/Met-museum-roof-garden-da-corte.html
-    https://www.forbes.com/sites/davidphelan/2024/07/09/apple-iphone-16-pro-major-design-upgrade-coming-new-report-claims/
-    https://www.crn.com/news/channel-programs/18828789/microsoft-to-release-windows-xp-service-pack-1
-    https://github.com/torvalds
-    https://www.rickbayless.com/recipe/pastor-style-tacos/
-        
-    Some websites, like x.com, are not accessible because they use JavaScript engines to load content, which is beyond the scope of this project.
+High Similarity to Training Data:
+https://www.nytimes.com/2007/01/10/technology/10apple.html
+https://www.nytimes.com/2021/04/15/arts/design/Met-museum-roof-garden-da-corte.html
+https://github.com/torvalds
+
+Less than 2% Overlap with Training Data:
+https://substack.com/browse/staff-picks/post/145699191
+https://brentcates.substack.com/p/julian-assange-is-now-free-to-collapse
+
+Moderate Similarity to Training Data:
+https://techcrunch.com/2024/07/05/openai-breach-is-a-reminder-that-ai-companies-are-treasure-troves-for-hackers/
+https://www.forbes.com/sites/davidphelan/2024/07/09/apple-iphone-16-pro-major-design-upgrade-coming-new-report-claims/
+https://www.crn.com/news/channel-programs/18828789/microsoft-to-release-windows-xp-service-pack-1
+https://www.rickbayless.com/recipe/pastor-style-tacos/
+
+No Similarity to Training Data:
+https://www.notioneverything.com/blog/notion-note-taking-templates
+https://www.eluniverso.com/noticias/ecuador/quito-prohibido-circular-dos-personas-moto-seguridad-nota/
+https://www.swift.org/blog/swift-on-windows/
+
+    Some websites, like x.com or instagram.com, are not accessible because they use JavaScript engines to load content, which is beyond the scope of this project.
 
 ```
             
@@ -166,12 +163,17 @@ Given the substantial volume of data, training a model from scratch was deemed i
 - 406M params
 
 
-            
+          
 ### Potential avenues for performance enhancement include:
 - Data preprocessing optimization
 - Dataset expansion
 - Comprehensive hyperparameter tuning
 - These strategies could significantly improve model efficacy.
+- Add more language in the dataset
+### Access to the Models
+`https://huggingface.co/wgcv/tidy-tab-model-t5-small`
+`https://huggingface.co/wgcv/tidy-tab-model-pegasus-xsum`
+`https://huggingface.co/wgcv/tidy-tab-model-bart-large-cnn`
 
 ## co2_eq_emissions
 - emissions: 0.16 grams of CO2)
@@ -186,3 +188,18 @@ Given the substantial volume of data, training a model from scratch was deemed i
 
 """, unsafe_allow_html=False, help=None)
 
+
+with st.sidebar.status("Loading models...", expanded=True, state="complete") as models:
+    st.write("Loading 1/3 (https://huggingface.co/wgcv/tidy-tab-model-t5-small)")
+    get_tidy_tab_t5()
+    st.write("Loaded T5-Small...")
+
+    st.write("Loading 2/3 (https://huggingface.co/wgcv/tidy-tab-model-pegasus-xsum)")
+    get_tidy_tab_pegasus()
+    st.write("Loaded Pegasus xsum...")
+
+    st.write("Loading 3/3 (https://huggingface.co/wgcv/tidy-tab-model-bart-large-cnn)")
+    load_model_bart()
+    st.write("Loaded Pegasus Bart-Large...")
+
+    models.update(label="All models loaded!", state="complete", expanded=False)