Hugging Face's logo

Spaces:
awacke1
/
AIZTH-03-09-2023
Running

App Files Community
1
awacke1 commited on
Commit
7631188
·
1 Parent(s): 608cef6

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +106 -51
app.py CHANGED
@@ -2,6 +2,112 @@ import streamlit as st
2
  from graphviz import Digraph
3
 
4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  st.markdown("""
6
 
7
  # 👋 Multiply your productivity by 100 times today using AI - Two easy ways to turbo boost your AI learning journey! 💻
@@ -35,57 +141,6 @@ st.markdown("""
35
  """)
36
 
37
 
38
- st.markdown("""
39
-
40
- # Multiply your productivity by 100 times today using AI:
41
- - Lets prove it with HuggingFace, Gradio, Streamlit, ChatGPT,and HTML/Javascript
42
- - My Progression:
43
- 1. 2021 - With AI Coding From Scratch **10 AI programs per year** = 1 AI Program per 36.5 days.
44
- 2. 2022 - Discovered HF Spaces. **200 AI Programs** = a little over .5 Programs per day.
45
- 3. 2023 - New process - **AI Pair Programming** ChatGPT+HF = 266 in Q1 (**1064 programs per year**)
46
- 4. Conclusion: Over 100x with this simple recipe.
47
-
48
- ## When focused using AI to write outline, simplify outline, generate examples, debug and curate:
49
- 1. **Record:** 30 working programs in 2 days on planned subject outline. (15/day)
50
- 2. Synopsis: Learning in the Loop - AI Pair programming expands your knowledge.
51
- 3. Use **Targeted AI vocabulary keywords** to generate domain specific code and text mashups.
52
-
53
- # How to Prompt using domain technical knowledge to accelerate process of design and development.
54
- 1. Top Ten Favorite Quick and Easy prompting patterns:
55
- 1. **Markdown** 1,2,3
56
- 1. **Prompt:** Create a markdown cheat sheet that lists all the commands and short instructions for performing markdown code.
57
- 2. **Trouble** with code versus non code due to delimiters like triple apostrophe? Its using markdown.
58
- 3. **Prompt:** Show full code listing in markdown code delimited by ``` with no comments
59
- 2. **Mermaid** for sorted and organized graphs.
60
- 3. **Python Streamlit** and Python gradio with code example input.
61
- 4. **Progressions** iterate with prompts to get what you want in a few steps..
62
- 1. **Prompt and Experiment:** Write an AI program using python, streamlit sklearn and keras to produce an AI program predicting sepal length.
63
- 2. **Curate and Revise:** Show full code listing. remove commentary. Make code listing as short as possible with few lines of code
64
- 3. **Reinforce and Teach:** Test and Share with HF to debug and test. Demonstrate and share links to others.
65
- 2. **Why does this work?** Copy and Modify Pattern, Mirroring, and the Human Brain.
66
- 3. **Life Lessons** from Steel Manufacturing - Innovation, Productivity
67
- 1. **US Steel** - Cost of not changing and 5%
68
- 2. **Tata Steel** - Employment, Karma, and Legends
69
-
70
- # HF Token - Create a new token in Settings for this code:
71
- HF_TOKEN = os.environ.get("HF_TOKEN") # get token from secrets, copy token value HF_TOKEN from Profile settings token into this repo settings
72
- generator2 = gr.Interface.load("huggingface/EleutherAI/gpt-neo-2.7B", api_key=HF_TOKEN) # add api_key=HF_TOKEN to get over the quota error
73
- generator3 = gr.Interface.load("huggingface/EleutherAI/gpt-j-6B", api_key=HF_TOKEN)
74
- generator1 = gr.Interface.load("huggingface/gpt2-large", api_key=HF_TOKEN)
75
- gr.Parallel(generator1, generator2, generator3, inputs=gr.inputs.Textbox(lines=5, label="Enter a sentence to get another sentence."),
76
- title=title, examples=examples).launch(share=False)
77
-
78
- # Access Tokens:
79
- ![image](https://user-images.githubusercontent.com/30595158/224001979-aba0c67d-dc28-44f8-bf13-cd01f9fe9b48.png)
80
-
81
- 3. Gradio Spaces - Lets set time records for copy/modify pattern
82
- 1. Concept, Examples, 3 AI Models: https://huggingface.co/spaces/awacke1/Sentence2Paragraph
83
- 2. Generative AI: https://huggingface.co/spaces/awacke1/Image-to-Line-Drawings
84
-
85
-
86
-
87
- """)
88
-
89
 
90
 
91
  st.markdown("""
 
2
  from graphviz import Digraph
3
 
4
 
5
+ st.markdown("""
6
+
7
+ # 👋 Multiply your productivity by 100 times today using AI:
8
+
9
+ 🌐 Lets prove it with HuggingFace, Gradio, Streamlit, ChatGPT,and HTML/Javascript
10
+ My Progression:
11
+ 1. 2021 - With AI Coding From Scratch **10 AI programs per year** = 1 AI Program per 36.5 days.
12
+ 2. 2022 - Discovered HF Spaces. **200 AI Programs** = a little over .5 Programs per day.
13
+ 3. 2023 - New process - **AI Pair Programming** ChatGPT+HF = 266 in Q1 (**1064 programs per year**)
14
+ 4. Conclusion: Over 100x with this simple recipe.
15
+
16
+ ## 🌐 When focused using AI to write outline, simplify outline, generate examples, debug and curate:
17
+ 1. **Record:** 30 working programs in 2 days on planned subject outline. (15/day)
18
+ 2. Synopsis: Learning in the Loop - AI Pair programming expands your knowledge.
19
+ 3. Use **Targeted AI vocabulary keywords** to generate domain specific code and text mashups.
20
+
21
+ # 🌐 How to Prompt using domain technical knowledge to accelerate process of design and development.
22
+ 1. Top Ten Favorite Quick and Easy prompting patterns:
23
+ 1. **Markdown** 1,2,3
24
+ 1. **Prompt:** Create a markdown cheat sheet that lists all the commands and short instructions for performing markdown code.
25
+ 2. **Trouble** with code versus non code due to delimiters like triple apostrophe? Its using markdown.
26
+ 3. **Prompt:** Show full code listing in markdown code with no comments
27
+ 2. **Mermaid** for sorted and organized graphs. -🌐 https://huggingface.co/spaces/awacke1/MermaidModelHTML5Demo
28
+ 3. **Python Streamlit** and Python gradio with code example input.
29
+ 4. **Progressions** iterate with prompts to get what you want in a few steps..
30
+ 1. **Prompt and Experiment:** Write an AI program using python, streamlit sklearn and keras to produce an AI program predicting sepal length.
31
+ 2. **Curate and Revise:** Show full code listing. remove commentary. Make code listing as short as possible with few lines of code
32
+ 3. **Reinforce and Teach:** Test and Share with HF to debug and test. Demonstrate and share links to others.
33
+ 2. **Why does this work?** Copy and Modify Pattern, Mirroring, and the Human Brain.
34
+ 3. **Life Lessons** from Steel Manufacturing - Innovation, Productivity
35
+ 1. **US Steel** - Cost of not changing and 5%
36
+ 2. **Tata Steel** - Employment, Karma, and Legends
37
+
38
+ # 🌐 HF Token - Create a new token in Settings for this code:
39
+ 1. HF_TOKEN = os.environ.get("HF_TOKEN") # get token from secrets, copy token value HF_TOKEN from Profile settings token into this repo settings
40
+ 2. generator2 = gr.Interface.load("huggingface/EleutherAI/gpt-neo-2.7B", api_key=HF_TOKEN) # add api_key=HF_TOKEN to get over the quota error
41
+ 3. generator3 = gr.Interface.load("huggingface/EleutherAI/gpt-j-6B", api_key=HF_TOKEN)
42
+ 4. generator1 = gr.Interface.load("huggingface/gpt2-large", api_key=HF_TOKEN)
43
+ 5. gr.Parallel(generator1, generator2, generator3, inputs=gr.inputs.Textbox(lines=5, label="Enter a sentence to get another sentence."),
44
+ title=title, examples=examples).launch(share=False)
45
+
46
+ # 🌐 Access Tokens:
47
+ ![image](https://user-images.githubusercontent.com/30595158/224001979-aba0c67d-dc28-44f8-bf13-cd01f9fe9b48.png)
48
+
49
+ # 🌐 Org Join:
50
+ 1. Org: https://huggingface.co/CognitiveAIForHealth
51
+ 2. Join Link: https://huggingface.co/organizations/CognitiveAIForHealth/share/LUIgWlwxqHYTeKWwVGOCaADIJNDBdtOfER
52
+ 3. Observe - Verify if you show up in Team list.
53
+
54
+ # 🌐 Gradio Spaces - Lets set time records for copy/modify pattern
55
+ 1. Concept, Examples, 3 AI Models: https://huggingface.co/spaces/awacke1/Sentence2Paragraph
56
+ 2. Generative AI: https://huggingface.co/spaces/awacke1/Image-to-Line-Drawings
57
+
58
+ # 🌐 Easy Button in Model Pages - Model Bakeoffs with Gradio:
59
+ 1. Task Search, find models
60
+ 2. Open 5, try model card tests
61
+ 3. Open 3 in new tab, Deploy Spaces.
62
+
63
+ # 🌐 Top Copy and Modify Examples
64
+ - Lets set time records for copy/modify pattern - Get these running in your account.
65
+ 1. **Cognitive, RLHF**: [Example 🩺⚕️](https://huggingface.co/spaces/awacke1/Cognitive-AI-Episodic-Semantic-Memory-Demo)
66
+ 2. **Big Science Bloom**: https://huggingface.co/spaces/awacke1/BigScienceContinualGenerator
67
+ 2. **Clinical Terminology** NER: [Example 🩺⚕️NLP Clinical Ontology Biomedical NER](https://huggingface.co/spaces/awacke1/Biomed-NLP-AI-Clinical-Terminology)
68
+ 3. **Torch and Git**: https://huggingface.co/spaces/awacke1/Image-to-Multilingual-OCR
69
+ 4. **Useful QA, NLP and Visualization Models**:
70
+ - Heatmap, Cluster: https://huggingface.co/spaces/awacke1/NLPSentenceSimilarityHeatmap
71
+ - QA Context: https://huggingface.co/spaces/awacke1/Question-answering
72
+ - Seq2Seq: https://huggingface.co/spaces/awacke1/4-Seq2SeqQAT5
73
+ - MLM: https://huggingface.co/spaces/awacke1/SOTA-MedEntity
74
+ 5. **Mapbox with Prompts**: https://huggingface.co/spaces/awacke1/StreamlitPydeckMapVisualViewStateForLatitudeLongitude
75
+
76
+ # Curated Copy and Modify:
77
+ # Advanced NLP ASR Examples:
78
+ 1. 🩺⚕️ https://huggingface.co/spaces/awacke1/ASR-High-Accuracy-Test
79
+ 3. 🩺⚕️ https://huggingface.co/spaces/awacke1/TTS-STT-Blocks
80
+ 4. 🩺⚕️ https://huggingface.co/spaces/awacke1/CloneAnyVoice
81
+
82
+ ❓ **🩺⚕️ Question answering** - Answer questions posed in natural language. [Example](https://huggingface.co/spaces/awacke1/Question-answering)
83
+ 📊 **🩺⚕️ Text classification** - Classify text into different categories. [Example](https://huggingface.co/spaces/awacke1/sileod-deberta-v3-base-tasksource-nli)
84
+ 💬 **🩺⚕️ Text generation** - Generate natural language text. [Example](https://huggingface.co/spaces/awacke1/Sentence2Paragraph)
85
+ 🆕 **🩺⚕️ Generation of new data**: Create new data that resembles existing data. [Example](https://huggingface.co/spaces/awacke1/GenAI-Generate-New-Data-Resembling-Example)
86
+ 📊 **Data synthesis**: Synthesize data from multiple sources to create new datasets. [Example](https://huggingface.co/spaces/awacke1/Data-Synthesizer-Synthesize-From-Multiple-Sources)
87
+ 📈 **🩺⚕️ Data augmentation**: Augment existing datasets to make them larger and more diverse. [Example](https://huggingface.co/spaces/awacke1/Data-Augmentation)
88
+ 🩺⚕️ Yolo Real Time Image Recognition from Webcam: https://huggingface.co/spaces/awacke1/Webcam-Object-Recognition-Yolo-n-Coco
89
+
90
+ 🩺⚕️ [ROUGE](https://huggingface.co/spaces/evaluate-metric/rouge)
91
+ 🩺⚕️ [BLEU](https://huggingface.co/spaces/evaluate-metric/bleu)
92
+
93
+ ## 🩺⚕️ Hospital Visualizations
94
+ 🩺⚕️ https://huggingface.co/spaces/awacke1/VizLib-TopLargeHospitalsMinnesota
95
+ 🩺⚕️ https://huggingface.co/spaces/awacke1/VizLib-TopLargeHospitalsNewJersey
96
+ 🩺⚕️ https://huggingface.co/spaces/awacke1/VizLib-TopLargeHospitalsMentalHealth
97
+ 🩺⚕️ https://huggingface.co/spaces/awacke1/VizLib-GraphViz-Folium-MapTopLargeHospitalsinWI
98
+
99
+ 🩺⚕️ Game Activity Graph: https://huggingface.co/spaces/awacke1/CardGameActivity-GraphViz
100
+ 🩺⚕️ SVG Card Generation: https://huggingface.co/spaces/awacke1/VizLib-SVGWrite-Streamlit
101
+
102
+ ## Clinical Smart on FHIR
103
+ 🩺⚕️ https://huggingface.co/spaces/awacke1/Assessment-By-Organs
104
+ 🩺⚕️ https://huggingface.co/spaces/awacke1/SMART-FHIR-Assessment-Test2
105
+ 🩺⚕️ https://huggingface.co/spaces/awacke1/FHIRLib-FHIRKit
106
+
107
+ """)
108
+
109
+
110
+
111
  st.markdown("""
112
 
113
  # 👋 Multiply your productivity by 100 times today using AI - Two easy ways to turbo boost your AI learning journey! 💻
 
141
  """)
142
 
143
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
144
 
145
 
146
  st.markdown("""