rocketry_roqeto_peft_model

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Model Description

<!-- Provide a longer summary of what this model is. -->

• 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]

<!-- Provide the basic links for the model. -->

• Repository: https://github.com/shadadu/Roqeto

Uses

This is a chat bot to support support study and research in rocket and space engineering.

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

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

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

Training Procedure

Fine tuning code is available at: https://github.com/shadadu/Roqeto

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Model Card Contact

Please message through Hugging Face: https://huggingface.co/shaddie
or GitHub: https://github.com/shadadu