Model Card for Model ID
Model Description
- Developed by: Shadrack Antwi (https://github.com/shadadu)
- Model type: CausalLM
- Language(s) (NLP): Python, Pytorch
- License: MIT
- Finetuned from model : TinyLlama/TinyLlama-1.1B-Chat-v1.0
Model Sources [optional]
- Repository: https://github.com/shadadu/Roqeto
Uses
This is a chat bot to support support study and research in rocket and space engineering.
How to Get Started with the Model
You can run the model from Hugging Face hub using the script: https://github.com/shadadu/Roqeto/blob/main/chat_streamlit.py
Training Details
Please refer to the Hugging Face model card of the model fine tuned from. Withe fine tuning, the base chat model was fine-tuned on rocketry and space systems data using parameter efficient training (PEFT), specifically Low Rank Adaptation(LoRA).
Training Data
Fine tuning data: https://huggingface.co/datasets/shaddie/rocketry_qas_dataset https://huggingface.co/datasets/shaddie/space_systems_qas_dataset
Training Procedure
Fine tuning code is available at: https://github.com/shadadu/Roqeto
Model Card Contact
Please message through Hugging Face: https://huggingface.co/shaddie
or GitHub: https://github.com/shadadu