metadata
license: apache-2.0
Installation
To install the necessary dependencies, run:
pip install huggingface_hub torch transformers datasets argparse
Download the Repository
Use the huggingface_hub to download the repository:
from huggingface_hub import snapshot_download
# Download the repository
repo_path = snapshot_download("RobbiePasquale/lightbulb")
print(f"Repository downloaded to: {repo_path}")
1. Train a Web Search Agent
Usage:
python main_menu.py --task train_agent
2. Use a Web Search Agent (Inference)
Description:
Utilizes the trained web search agent to process queries, perform web searches, and generate summarized responses.
Usage:
python main_menu.py --task test_agent
Options:
- Interactive Mode:
python main_menu.py --task test_agent - Single Query Mode:
python main_menu.py --task test_agent --query "Your query here"
3. Train Language Model
Usage:
python main_menu.py --task train_llm_world --model_name gpt2 --dataset_name wikitext --num_epochs 5 --batch_size 8 --max_length 256
Key Arguments:
--model_name: Pretrained model (e.g.,gpt2,bert).--dataset_name: Dataset from Hugging Face (e.g.,wikitext).--num_epochs: Number of training epochs.--batch_size: Number of samples per batch.--max_length: Maximum sequence length.
4. Inference Using Language Model
Usage:
python main_menu.py --task inference_llm --query "Your query here"
5. Train World Model
Description:
Develops a comprehensive World Model that encapsulates state representations, dynamics, and prediction networks to simulate and predict state transitions within the Tree of Thought framework.
Usage:
python main_menu.py --task train_world_model --additional_args
6. Inference with Language World Model
Usage:
python main_menu.py --task inference_world_model --query "Your query here"
7. Advanced Inference
Usage:
python main_menu.py --task advanced_inference --query "Your complex query here"
Training the World Model
python main_menu.py --task train_llm_world --model_name gpt2 --dataset_name wikitext --num_epochs 5 --batch_size 8 --max_length 256
Training the Web Search Agent
python main_menu.py --task train_agent
Use the Web Search Agent in Interactive Mode
python main_menu.py --task test_agent
Use the Web Search Agent with a Single Query
python main_menu.py --task test_agent --query "What are the impacts of renewable energy on global sustainability?"
Inference with World Model and Tree of Thought
python main_menu.py --task advanced_inference --query "Analyze the economic effects of artificial intelligence in the next decade."
Citation
If you use LightBulb in your research, please cite the author:
@misc{RobbiePasquale_lightbulb,
author = {Robbie Pasquale},
title = {LightBulb: An Autonomous Web Search and Language Model Framework},
year = {2024},
publisher = {Huggingface},
howpublished = {\url{https://huggingface.co/RobbiePasquale/lightbulb}},
}
License
This project is licensed under the Apache 2.0 License.