This model is a finetuned version of Llama 3.2 specifically designed to answer questions related to the Robot Operating System (ROS). It was finetuned on Kaggle using domain-specific data scraped from GitHub repositories and Medium articles. The model powers a Retrieval-Augmented Generation (RAG) pipeline in our AI final project.
The model is used in a Retrieval-Augmented Generation (RAG) pipeline for answering questions related to the Robot Operating System (ROS). It integrates with a vector search engine (Qdrant) and MongoDB for efficient retrieval and query response generation.
The model can be extended for other technical domains through additional finetuning or plug-in integration into larger AI systems.
The model is not designed for tasks outside of technical documentation retrieval and answering ROS-related queries.
1from transformers import AutoModel, AutoTokenizer
2
3model = AutoModel.from_pretrained("your-model-id")
4tokenizer = AutoTokenizer.from_pretrained("your-model-id")
5
6input_text = "How can I navigate to a specific pose using ROS?"
7inputs = tokenizer(input_text, return_tensors="pt")
8outputs = model(**inputs)
9print(outputs)
1@misc{kapoor2024rosquery,
2 title={ROS Query System: A Retrieval-Augmented Generation Pipeline},
3 author={Shresth Kapoor and Krish Murjani},
4 year={2024},
5 note={CS-GY-6613 AI Final Project, NYU Tandon School of Engineering}
6}
For any inquiries, please contact us through our (
GitHub Repository).
