ankiGPT-small / README.md
anktechsol's picture
Update README.md
b8f1a1c verified
---
license: mit
datasets:
- ai4bharat/indic-align
language:
- en
metrics:
- accuracy
base_model:
- microsoft/DialoGPT-small
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
---
# anktechsol/ankiGPT-small
## 🧠 What is ankiGPT-small?
A conversational **text-generation** model fine-tuned from `microsoft/DialoGPT-small` for Indian scenarios—supporting English and Hinglish. Use it to generate stories, dialogue, quick responses, and creative text.
---
## 🚀 Quick Start
```python
from transformers import pipeline
generator = pipeline("text-generation", model="anktechsol/ankiGPT-small")
prompt = "Write a short story about a day in the life of a student in a bustling Indian city."
result = generator(prompt, max_length=300, num_return_sequences=1)
print(result[0]['generated_text'])
```
*Copy-paste this code to see instant results!*
---
## ✨ Features
- **Conversational:** Tuned for chat, stories, and messages
- **Language:** English + Hinglish (Indian conversational flavor)
- **Base Model:** DialoGPT-small
- **Size:** 124M parameters (fast and lightweight)
- **Dataset:** ai4bharat/indic-align (Indian context data)
---
## 💡 Example Outputs
> **Prompt:** "Describe the Diwali celebrations in Mumbai."
>
> **Output:** "The city sparkled with thousands of lights, families prepared delicious sweets, and friends gathered for bursting crackers, laughter echoing through the alleys."
>
> *Try your own prompts above!*
---
## ⚠️ Limitations & Considerations
- Tends to repeat on long text—adjust `max_length` and `no_repeat_ngram_size` as needed
- Biased towards Indian contexts due to training data
- Not for critical or factual information generation
---
## 🙌 Contributions & Community
- **Suggestions?** Open an issue or start a discussion. We welcome community feedback!
- **Demo:** Want a hands-on demo? Let us know!
---
## 🔗 References
- [anktechsol.com](https://www.anktechsol.com)
---