https://github.com/bhuvanyu09/text-completion-generator

https://github.com/bhuvanyu09/text-completion-generator

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (12.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: bhuvanyu09
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 12.7 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme License

README.md

GEN-AI


````markdown

🧠 Text Completion Generator

Python License Model Transformers

A terminal-based AI-powered text completion tool that leverages Hugging Face Transformers and PyTorch to generate coherent and creative continuations of input prompts. Comes with both an interactive shell and CLI support for flexible usage.


✨ Features

  • ✅ Easy-to-use command-line interface
  • ✅ Interactive mode with real-time settings adjustment
  • ✅ Supports any Hugging Face causal language model (e.g., gpt2, EleutherAI/gpt-neo)
  • ✅ Fine-tuned parameters: temperature, top_k, top_p, etc.
  • ✅ Rich terminal UI via the rich library
  • ✅ GPU acceleration with CUDA (if available)

📦 Installation

Clone the repository and install the required packages:

bash git clone https://github.com/yourusername/text-completion-generator.git cd text-completion-generator pip install -r requirements.txt `

Requirements

  • Python 3.7+
  • PyTorch (>=1.9.0)
  • Transformers (>=4.18.0)
  • Rich (>=12.0.0)

🚀 Usage

🔁 Interactive Mode

bash python 1.py --interactive

  • Type any prompt to generate completions.
  • Adjust settings like temperature or max_length by typing settings.
  • Exit with exit or quit.

💬 Single-Prompt Mode

bash python 1.py --prompt "Once upon a time" --max-length 100 --temperature 0.7 --num-sequences 2

💻 Force CPU/GPU

bash python 1.py --prompt "The future of AI is" --device cpu


⚙️ Command-Line Arguments

| Flag | Description | Default | | ----------------- | ------------------------------------------------- | ------- | | --model | Hugging Face model name (e.g., gpt2, gpt-neo) | gpt2 | | --prompt | Prompt text for one-shot completion | — | | --max-length | Maximum length of generated text | 50 | | --temperature | Controls creativity/randomness of output | 0.8 | | --top-k | Top-k sampling cutoff | 50 | | --top-p | Nucleus sampling probability threshold | 0.9 | | --num-sequences | Number of completion outputs | 1 | | --interactive | Enable interactive CLI mode | False | | --device | cpu or cuda; auto-detect if not set | Auto |


🧪 Example Output

``` Enter text to complete: The secret to happiness is

Completions: ──────────────────────────────────────────────── The secret to happiness is accepting who you are and finding peace in the present moment. ──────────────────────────────────────────────── ```


🛠 Built With


📄 License

This project is open-sourced under the MIT License.


🙌 Acknowledgements

Thanks to the Hugging Face team and the open-source community for building accessible NLP tools.

```

Owner

  • Name: Bhuvanyu Geel
  • Login: bhuvanyu09
  • Kind: user

Hello everyone! I am pursuing my Bachelors of technology from Vellore Institute of Technology in Computer Science and Engineering

GitHub Events

Total
Last Year

Dependencies

requirements.txt pypi
  • rich >=12.0.0
  • torch >=1.9.0
  • transformers >=4.18.0