predacons-cli 0.0.100

comand line interface for Predacons

Predacons CLI

Welcome to the Predacons CLI! This command-line interface (CLI) allows you to interact with the Predacons library, providing a seamless way to load models, generate responses, and manage configurations directly from your terminal.

Features

• Model Management: Load and manage different types of models including local, Hugging Face safetensor, PyTorch, and GGUF models.
• Interactive Chat: Engage in interactive chat sessions with the loaded model.
• Configuration Management: Easily create, update, and clear configuration files.
• Rich Output: Utilize rich text formatting for better readability and user experience.
• Logging: Optionally enable logging for debugging and tracking purposes.

Installation

To install the Predacons CLI, you need to have Python installed on your system. You can install the required dependencies using pip:

pip install -r requirements.txt

Usage

Launching the CLI

To start the Predacons CLI, simply run:

python cli.py

Commands

Once the CLI is launched, you can use the following commands:

• clear: Clear the chat history.
• exit: Quit the CLI.
• clear-config: Clear the current configuration file.
• settings: Show and update settings.
• version: Display the current version of the Predacons CLI.
• help: Show help information.

Example Session

$ python cli.py
Welcome to the Predacons CLI!
No config file found. Creating one now...
Creating a new configuration file...
Please enter the following details to create a new configuration file
...
Welcome to the Predacons CLI! Model: Precacons/Pico-Lamma-3.2-1B-Reasoning-Instruct loaded successfully!
You can start chatting with Predacons now. Type 'clear' to clear history, Type 'exit' to quit, Type 'help' for more options,
User: Hello!
Predacons: Hi there! How can I assist you today?

Configuration

The configuration file is stored at ~/.predacons_cli/predacon_cli_config.json. You can update the configuration settings by using the settings command within the CLI.

Configuration Options

• model_path: Path to the model or Hugging Face model name.
• trust_remote_code: Boolean to trust remote code.
• use_fast_generation: Boolean to enable fast generation.
• draft_model_name: Optional draft model name.
• gguf_file: Path to the GGUF file.
• auto_quantize: Boolean to enable auto quantization.
• temperature: Temperature setting for response generation.
• max_length: Maximum length for each response.
• top_k: Top K value for response generation.
• top_p: Top P value for response generation.
• repetition_penalty: Repetition penalty value.
• num_return_sequences: Number of return sequences.
• print_as_markdown: Boolean to print response as markdown.

Logging

To enable logging, launch the CLI with the --logs flag:

python cli.py --logs

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contributing

Contributions are welcome! Please open an issue or submit a pull request on GitHub.

Contact

For any questions or support, please open an issue on the GitHub repository.

---

Enjoy using the Predacons CLI! 🚀