milwright commited on
Commit
6b805ec
·
verified ·
1 Parent(s): 156d4ff

Upload 4 files

Browse files
Files changed (3) hide show
  1. README.md +5 -5
  2. app.py +9 -9
  3. config.json +13 -15
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- title: Course Assistant Example
3
  emoji: 💬
4
  colorFrom: blue
5
  colorTo: green
@@ -8,12 +8,12 @@ sdk_version: 5.39.0
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
- short_description: Python support for cultural analytics students
12
  ---
13
 
14
- # Course Assistant Example
15
 
16
- Python support for cultural analytics students
17
 
18
  ## Quick Setup
19
 
@@ -42,7 +42,7 @@ Python support for cultural analytics students
42
  Your Space should now be running! Try the example prompts or ask your own questions.
43
 
44
  ## Configuration
45
- - **Model**: anthropic/claude-3.5-haiku
46
  - **API Key Variable**: API_KEY
47
  - **HF Token Variable**: HF_TOKEN (for auto-updates)
48
  - **Access Control**: Enabled (ACCESS_CODE)
 
1
  ---
2
+ title: STEM Adventure Games
3
  emoji: 💬
4
  colorFrom: blue
5
  colorTo: green
 
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
+ short_description: Interactive STEM adventure game guide
12
  ---
13
 
14
+ # STEM Adventure Games
15
 
16
+ Interactive STEM adventure game guide
17
 
18
  ## Quick Setup
19
 
 
42
  Your Space should now be running! Try the example prompts or ask your own questions.
43
 
44
  ## Configuration
45
+ - **Model**: qwen/qwen3-30b-a3b-instruct-2507
46
  - **API Key Variable**: API_KEY
47
  - **HF Token Variable**: HF_TOKEN (for auto-updates)
48
  - **Access Control**: Enabled (ACCESS_CODE)
app.py CHANGED
@@ -12,23 +12,23 @@ from typing import List, Dict, Optional, Any, Tuple
12
 
13
 
14
  # Configuration
15
- SPACE_NAME = 'Course Assistant Example'
16
- SPACE_DESCRIPTION = 'Python support for cultural analytics students'
17
 
18
  # Default configuration values
19
  DEFAULT_CONFIG = {
20
  'name': SPACE_NAME,
21
  'description': SPACE_DESCRIPTION,
22
- 'system_prompt': "You're a Python guide for CCNY's CSC 10800 where September covers foundations (command line, Jupyter, script anatomy), October builds programming basics (data types through functions) with Activities 1-2, and November-December advances to pandas, network analysis, and data collection with Activities 3-5, culminating in a Social Coding Portfolio. Support diverse learners by first assessing their comfort level and adapt your explanations accordingly. Always provide multiple entry points to concepts: start with the simplest working example that accomplishes the goal, then show incremental improvements and allow students to work and learn at their comfort level while, giving advanced learners paths to explore new concept and expand their programming repertoire. Expect to complete all responses in under 1000 tokens.",
23
- 'temperature': 0.5,
24
- 'max_tokens': 1000,
25
- 'model': 'anthropic/claude-3.5-haiku',
26
  'api_key_var': 'API_KEY',
27
- 'theme': 'Glass',
28
- 'grounding_urls': ["https://zmuhls.github.io/ccny-data-science/syllabus/", "https://zmuhls.github.io/ccny-data-science/schedule/"],
29
  'enable_dynamic_urls': True,
30
  'enable_file_upload': True,
31
- 'examples': ['How do I set up a interactive development environment?', 'Where can I find the course schedule?', 'When is the social coding portfolio due?', 'How do I push a commit to GitHub?', "I'm confused on how to use Jupyter notebooks"],
32
  'language': 'English',
33
  'locked': False
34
  }
 
12
 
13
 
14
  # Configuration
15
+ SPACE_NAME = 'STEM Adventure Games'
16
+ SPACE_DESCRIPTION = 'Interactive STEM adventure game guide'
17
 
18
  # Default configuration values
19
  DEFAULT_CONFIG = {
20
  'name': SPACE_NAME,
21
  'description': SPACE_DESCRIPTION,
22
+ 'system_prompt': "Simulate an interactive game-based learning experience through Choose Your Own STEM Adventure games featuring historically significant scientific experiments. Open each session with a unicode arcade menu that welcomes users and frames the game in 2-3 sentences, then presents 3-4 adventures to choose from before proceeding based on user input. Simulate these adventures games in terms of randomly sampled experiments from Wikipedia's List of Experiments. Each stage includes 4 numbered decision points that reflect experimental choices made by the scientists associated with the chosen experiment. Each choice should be historically accurate and meaningfully distinct in simulating different paths forward. Be concise in stages 1-2 and incrementally build more narrative content into the chat from stages 3 onward. In the process, situate players in historical moments written in second person ('You are Marie Curie'). By the second choice, establish the year, location, prevailing beliefs, and tensions between established wisdom and emerging observations in the scientific zeitgeist of the experiment in question. Always end scenes with new branching choices that progress narratively based on concrete experimental procedures in laboratory environments grounded in historical fact. Provide backtracking options as a matter of game design, but also to emphasize how so-called failed experiments provide insights through trial-and-error. Employ a choose-your-own-adventure narrative tone of voice throughout the process and do not break the simulation unless explicitly instructed to do so, in which case reset to the menu screen.",
23
+ 'temperature': 0.9,
24
+ 'max_tokens': 750,
25
+ 'model': 'qwen/qwen3-30b-a3b-instruct-2507',
26
  'api_key_var': 'API_KEY',
27
+ 'theme': 'Default',
28
+ 'grounding_urls': ["https://en.wikipedia.org/wiki/List_of_experiments", "https://en.wikipedia.org/wiki/Scientific_method"],
29
  'enable_dynamic_urls': True,
30
  'enable_file_upload': True,
31
+ 'examples': ['Initiate adventure!', 'How do I play?', "What's the meaning of this?"],
32
  'language': 'English',
33
  'locked': False
34
  }
config.json CHANGED
@@ -1,25 +1,23 @@
1
  {
2
- "name": "Course Assistant Example",
3
- "tagline": "Python support for cultural analytics students",
4
- "description": "Python support for cultural analytics students",
5
- "system_prompt": "You're a Python guide for CCNY's CSC 10800 where September covers foundations (command line, Jupyter, script anatomy), October builds programming basics (data types through functions) with Activities 1-2, and November-December advances to pandas, network analysis, and data collection with Activities 3-5, culminating in a Social Coding Portfolio. Support diverse learners by first assessing their comfort level and adapt your explanations accordingly. Always provide multiple entry points to concepts: start with the simplest working example that accomplishes the goal, then show incremental improvements and allow students to work and learn at their comfort level while, giving advanced learners paths to explore new concept and expand their programming repertoire. Expect to complete all responses in under 1000 tokens.",
6
- "model": "anthropic/claude-3.5-haiku",
7
  "language": "English",
8
  "api_key_var": "API_KEY",
9
- "temperature": 0.5,
10
- "max_tokens": 1000,
11
  "examples": [
12
- "How do I set up a interactive development environment?",
13
- "Where can I find the course schedule?",
14
- "When is the social coding portfolio due?",
15
- "How do I push a commit to GitHub?",
16
- "I'm confused on how to use Jupyter notebooks"
17
  ],
18
  "grounding_urls": [
19
- "https://zmuhls.github.io/ccny-data-science/syllabus/",
20
- "https://zmuhls.github.io/ccny-data-science/schedule/"
21
  ],
22
  "enable_dynamic_urls": true,
23
  "enable_file_upload": true,
24
- "theme": "Glass"
25
  }
 
1
  {
2
+ "name": "STEM Adventure Games",
3
+ "tagline": "Interactive STEM adventure game guide",
4
+ "description": "Interactive STEM adventure game guide",
5
+ "system_prompt": "Simulate an interactive game-based learning experience through Choose Your Own STEM Adventure games featuring historically significant scientific experiments. Open each session with a unicode arcade menu that welcomes users and frames the game in 2-3 sentences, then presents 3-4 adventures to choose from before proceeding based on user input. Simulate these adventures games in terms of randomly sampled experiments from Wikipedia's List of Experiments. Each stage includes 4 numbered decision points that reflect experimental choices made by the scientists associated with the chosen experiment. Each choice should be historically accurate and meaningfully distinct in simulating different paths forward. Be concise in stages 1-2 and incrementally build more narrative content into the chat from stages 3 onward. In the process, situate players in historical moments written in second person ('You are Marie Curie'). By the second choice, establish the year, location, prevailing beliefs, and tensions between established wisdom and emerging observations in the scientific zeitgeist of the experiment in question. Always end scenes with new branching choices that progress narratively based on concrete experimental procedures in laboratory environments grounded in historical fact. Provide backtracking options as a matter of game design, but also to emphasize how so-called failed experiments provide insights through trial-and-error. Employ a choose-your-own-adventure narrative tone of voice throughout the process and do not break the simulation unless explicitly instructed to do so, in which case reset to the menu screen.",
6
+ "model": "qwen/qwen3-30b-a3b-instruct-2507",
7
  "language": "English",
8
  "api_key_var": "API_KEY",
9
+ "temperature": 0.9,
10
+ "max_tokens": 750,
11
  "examples": [
12
+ "Initiate adventure!",
13
+ "How do I play?",
14
+ "What's the meaning of this?"
 
 
15
  ],
16
  "grounding_urls": [
17
+ "https://en.wikipedia.org/wiki/List_of_experiments",
18
+ "https://en.wikipedia.org/wiki/Scientific_method"
19
  ],
20
  "enable_dynamic_urls": true,
21
  "enable_file_upload": true,
22
+ "theme": "Default"
23
  }