Update comprehensive model card for STACKS
Browse files
README.md
CHANGED
|
@@ -26,7 +26,7 @@ model_type: gemma
|
|
| 26 |
|
| 27 |
STACKS transforms any role or profession into detailed, engaging prompts perfect for:
|
| 28 |
- **Role-playing games** and creative writing
|
| 29 |
-
- **Educational scenarios** and training simulations
|
| 30 |
- **Content creation** and storytelling
|
| 31 |
- **Character development** exercises
|
| 32 |
|
|
@@ -50,13 +50,13 @@ return response[len(input_text):].strip()
|
|
| 50 |
|
| 51 |
## 📋 Example Outputs
|
| 52 |
|
| 53 |
-
**Input:** `"chef"`
|
| 54 |
**STACKS Output:** *"Act as a world-renowned chef who specializes in fusion cuisine. You've just opened a new restaurant that combines traditional techniques with molecular gastronomy. Explain your signature dish and the story behind its creation."*
|
| 55 |
|
| 56 |
-
**Input:** `"time traveler"`
|
| 57 |
**STACKS Output:** *"You are a time traveler who has just arrived in the year 2024 from 1850. Describe your amazement at modern technology, but also share wisdom from the past that people today have forgotten."*
|
| 58 |
|
| 59 |
-
**Input:** `"detective"`
|
| 60 |
**STACKS Output:** *"Act as a private detective in 1940s noir-style setting. You've been hired to investigate a mysterious disappearance at a high-society party. Describe the case and your first impressions of the suspects."*
|
| 61 |
|
| 62 |
## 🎭 Supported Role Categories
|
|
@@ -64,7 +64,7 @@ return response[len(input_text):].strip()
|
|
| 64 |
STACKS excels at generating prompts for:
|
| 65 |
|
| 66 |
- **Professional Roles**: doctors, lawyers, teachers, engineers, scientists
|
| 67 |
-
- **Creative Roles**: artists, writers, musicians, designers, filmmakers
|
| 68 |
- **Historical Figures**: philosophers, explorers, inventors, rulers
|
| 69 |
- **Fictional Characters**: superheroes, fantasy characters, sci-fi roles
|
| 70 |
- **Specialized Experts**: consultants, coaches, advisors, mentors
|
|
@@ -75,13 +75,13 @@ STACKS excels at generating prompts for:
|
|
| 75 |
### Training Configuration
|
| 76 |
- **Base Model**: google/gemma-3-270m (268M parameters)
|
| 77 |
- **Training Type**: Complete fine-tuning (all parameters trainable)
|
| 78 |
-
- **Dataset**: fka/awesome-chatgpt-prompts
|
| 79 |
- **Format**: Role → Prompt generation patterns
|
| 80 |
- **Precision**: BF16 optimized
|
| 81 |
- **Context Length**: 768 tokens
|
| 82 |
- **Training Date**: 2025-08-20
|
| 83 |
|
| 84 |
-
### Model Specifications
|
| 85 |
- **Architecture**: Gemma-3
|
| 86 |
- **Parameters**: 268,098,176
|
| 87 |
- **Format**: Safetensors
|
|
@@ -93,7 +93,7 @@ STACKS excels at generating prompts for:
|
|
| 93 |
|
| 94 |
STACKS generates:
|
| 95 |
- **Coherent prompts** that match the requested role
|
| 96 |
-
- **Creative scenarios** with engaging storylines
|
| 97 |
- **Detailed instructions** for effective role-playing
|
| 98 |
- **Varied outputs** avoiding repetitive patterns
|
| 99 |
- **Contextually appropriate** content for each role
|
|
@@ -109,5 +109,5 @@ This model is released under the **Gemma License**. Please see the [Gemma Licens
|
|
| 109 |
|
| 110 |
---
|
| 111 |
|
| 112 |
-
**Built with ❤️ by gouthamsai78**
|
| 113 |
*Transforming roles into creative prompts, one generation at a time.*
|
|
|
|
| 26 |
|
| 27 |
STACKS transforms any role or profession into detailed, engaging prompts perfect for:
|
| 28 |
- **Role-playing games** and creative writing
|
| 29 |
+
- **Educational scenarios** and training simulations
|
| 30 |
- **Content creation** and storytelling
|
| 31 |
- **Character development** exercises
|
| 32 |
|
|
|
|
| 50 |
|
| 51 |
## 📋 Example Outputs
|
| 52 |
|
| 53 |
+
**Input:** `"chef"`
|
| 54 |
**STACKS Output:** *"Act as a world-renowned chef who specializes in fusion cuisine. You've just opened a new restaurant that combines traditional techniques with molecular gastronomy. Explain your signature dish and the story behind its creation."*
|
| 55 |
|
| 56 |
+
**Input:** `"time traveler"`
|
| 57 |
**STACKS Output:** *"You are a time traveler who has just arrived in the year 2024 from 1850. Describe your amazement at modern technology, but also share wisdom from the past that people today have forgotten."*
|
| 58 |
|
| 59 |
+
**Input:** `"detective"`
|
| 60 |
**STACKS Output:** *"Act as a private detective in 1940s noir-style setting. You've been hired to investigate a mysterious disappearance at a high-society party. Describe the case and your first impressions of the suspects."*
|
| 61 |
|
| 62 |
## 🎭 Supported Role Categories
|
|
|
|
| 64 |
STACKS excels at generating prompts for:
|
| 65 |
|
| 66 |
- **Professional Roles**: doctors, lawyers, teachers, engineers, scientists
|
| 67 |
+
- **Creative Roles**: artists, writers, musicians, designers, filmmakers
|
| 68 |
- **Historical Figures**: philosophers, explorers, inventors, rulers
|
| 69 |
- **Fictional Characters**: superheroes, fantasy characters, sci-fi roles
|
| 70 |
- **Specialized Experts**: consultants, coaches, advisors, mentors
|
|
|
|
| 75 |
### Training Configuration
|
| 76 |
- **Base Model**: google/gemma-3-270m (268M parameters)
|
| 77 |
- **Training Type**: Complete fine-tuning (all parameters trainable)
|
| 78 |
+
- **Dataset**: fka/awesome-chatgpt-prompts
|
| 79 |
- **Format**: Role → Prompt generation patterns
|
| 80 |
- **Precision**: BF16 optimized
|
| 81 |
- **Context Length**: 768 tokens
|
| 82 |
- **Training Date**: 2025-08-20
|
| 83 |
|
| 84 |
+
### Model Specifications
|
| 85 |
- **Architecture**: Gemma-3
|
| 86 |
- **Parameters**: 268,098,176
|
| 87 |
- **Format**: Safetensors
|
|
|
|
| 93 |
|
| 94 |
STACKS generates:
|
| 95 |
- **Coherent prompts** that match the requested role
|
| 96 |
+
- **Creative scenarios** with engaging storylines
|
| 97 |
- **Detailed instructions** for effective role-playing
|
| 98 |
- **Varied outputs** avoiding repetitive patterns
|
| 99 |
- **Contextually appropriate** content for each role
|
|
|
|
| 109 |
|
| 110 |
---
|
| 111 |
|
| 112 |
+
**Built with ❤️ by gouthamsai78**
|
| 113 |
*Transforming roles into creative prompts, one generation at a time.*
|