Artificial intelligence LLM

@tadinhkien

Greetings, Thank you for considering my application for this project. As an AI Engineer and Python Developer with over 8+ years of experience, I bring a wealth of knowledge and expertise in the field of Python, Deep Learning. I have carefully reviewed the project description and am eager to discuss your specific needs and requirements in more detail. My commitment is to provide dedicated support and consistent follow-up throughout the project's lifecycle. Please feel free to reach out to me to further discuss how I can contribute to the success of your project. Looking forward to the opportunity of working together. Best regards, KuroKien

@mzdesmag

Hello sir, Did go through your job description and glad to share that I have enormous experience in working with Artificial intelligence LLM I'm a seasoned programmer and Engineer with quality experience in Flutter, React, Node.JS, SpringBoot, Frontend and Backend Development, Python, Matlab, R studio, C, C++, C#, OpenCV, OpenGL, Tesseract OCR, google vision, Statistical programming/R progamming data analysis Computing for Data Analysis Time Series & Econometric, Machine learning, AI, Deep learning, Matlab and Mathematica, 3D modeling, CAD/CAM,AutoCAD, 2D, Architectural Engineering, SolidWorks, Unity 3D, PCB, Electronics, Arduino, Automation, Embedded and Firmware , IOT, Electrical/Mechanical Engineering I am a TOP Rated Freelancer, and you can check my reviews here as well: https://www.freelancer.com/u/mzdesmag. Looking forward to potentially working together on this project. Thanks and Best regards, Adekunle.

@arbu1499

Hello, I can help you structure and build your full Colab-ready Jupyter Notebook for the XSum summarisation assignment following the required steps (zero-shot, few-shot, prompt engineering, evaluation table, and 200-word analysis), including proper Hugging Face dataset handling, model selection (e.g., T5/BART/FLAN-T5 depending on constraints), train/test splitting, preprocessing functions, and evaluation using suitable metrics like ROUGE with clear comparison across all four approaches in a single clean, Moodle-compliant template. I’ll ensure the notebook is well-commented, reproducible in Google Colab, and fully aligned with academic requirements so you can directly submit it with outputs included. Looking forward for your positive response in the chatbox. Best Regards, Arbaz N

@ionstefanache1

Hi, I can do that for you using GCP(.ipynb) or locally on my GPU(RTX4060 / 8GB VRAM under Ubuntu 24.04 LTS). If agree this please let me know Thanks

@rishi9343

I will build a solution using a Large Language Model from Hugging Face, specifically adapting it to solve a summarization task on the EdinburghNLP/xsum dataset, following the provided template and using approaches such as zero-shot learning, few-shot learning, and prompt engineering, to deliver a Jupyter notebook file with all code outputs included, which can be run via Google Colab, and provide a brief discussion on results interpretation, including findings, surprising errors, and benchmark vs

@bohdan38

❤️❤️❤️❤️❤️Hi,You need to adapt an LLM to perform XSum summarisation and the issue is selecting and configuring the model/training pipeline so results are reproducible and Colab-compatible , this often happens because default splits, tokenization and trainer settings aren’t tailored to long articles. Solution: 1) Choose a lightweight Seq2Seq LLM (e.g., T5-small or BART-base), split dataset (train/val/test), implement HF data processing and tokenization; 2) Run zero-shot and few-shot evaluations, then apply prompt engineering (length/style constraints) and evaluate; 3) Log metrics (ROUGE) and compile results in the required Moodle template. I previously fine-tuned BART-base on CNN/DailyMail with ROUGE improvements of +5 points. Smart suggestion: use dynamic padding and gradient accumulation to fit GPU limits. What compute (Colab Pro/Pro+) will you use and any model preference?Which Colab tier and GPU will you have access to, and do you prefer T5 or BART for this task? Best regards, Bohdan

@gugahb

I have over 10 years of experience in Artificial Intelligence and have carefully reviewed the project requirements. I am confident in my ability to execute this project with precision. Let's discuss further details in the chat. Thank you.

@shawanay

I can complete your LLM summarisation assignment tailored to your requirements, including features such as dataset preparation, zero-shot and few-shot evaluation, prompt engineering, and performance comparison using appropriate metrics. The system will include a fully structured Jupyter Notebook with code, outputs, evaluation table, and a concise results interpretation as per the provided template. Best regards, Shawana

@matheussilva114

Hi there! THE CHALLENGE is to effectively compare different approaches in adapting a Large Language Model (LLM) for a summarization task using the provided dataset. One potential difficulty could be selecting the most suitable LLM considering computational constraints and ensuring the data processing function, data split, and trainer configuration are properly defined. Additionally, implementing zero-shot, few-shot learning, and prompt engineering techniques may pose challenges in terms of articulating instructions, constraints, and assessing model performance accurately. To address these challenges, I would carefully research and analyze various LLM options, optimize data preprocessing steps, and meticulously document the implementation process in the Jupyter notebook to ensure clarity and reproducibility. Regards, Matheus.

@GenePauly

Hi, This is Gene from Luxembourg You need a Jupyter notebook that compares zero shot, few shot, and prompt engineering approaches on the XSum dataset with proper evaluation and discussion. I’ll set up a clean Colab notebook using a suitable Hugging Face model, handle dataset splits and preprocessing, then run each method consistently and present results in a clear comparison table. I’ve worked on LLM fine tuning and evaluation tasks before, including summarization workflows with Hugging Face and building notebooks that meet academic submission requirements with reproducible outputs. I’ll deliver a fully working notebook with all outputs, markdown explanations, and the 200 word analysis included. Delivery time will be 2 days. Quick question, do you have a preferred model or should I choose one optimized for Colab limits like FLAN T5 or BART?

@aimansulaiman

Hello, I would be glad to assist you with completing this LLM-based summarisation assignment in a structured and reproducible way using a Google Colab–compatible Jupyter Notebook. I understand the requirement to evaluate different approaches (zero-shot, few-shot, and prompt engineering) using the XSum dataset, and to present results clearly following the Moodle template. My approach: • Select a suitable Hugging Face model (e.g., FLAN-T5 or similar) considering Colab constraints • Prepare the dataset (train/validation/test split, preprocessing, tokenization) • Implement zero-shot evaluation on the test set • Implement few-shot prompting and evaluation • Apply prompt engineering (both zero- and few-shot) with clear constraints • Evaluate performance using an appropriate metric (e.g., ROUGE) • Create a results table comparing all approaches • Provide a concise (≤200 words) interpretation of findings, errors, and performance differences • Ensure all code runs cleanly in Google Colab with outputs included The final deliverable will strictly follow your Moodle template, with clean code, markdown explanations, and reproducible results. I can begin immediately and deliver within a short timeframe depending on your deadline. Thank you for your consideration.

@viktorh29

Hi, I can help you complete this assignment in a clean, well-structured, and fully reproducible way using Google Colab. I’ll implement and compare zero-shot, few-shot, and prompt-engineered approaches on the XSum dataset, ensuring proper data handling, evaluation on the test split only, and clear metric-based comparison (e.g., ROUGE). The notebook will follow your Moodle template closely, include all outputs, and be easy to run and modify. I’ll also provide a concise and well-reasoned analysis of the results, highlighting performance differences and any unexpected behaviors. Everything will be organized, documented, and ready for submission. Best

@bondoc0526

༺❖༻ Dear Client ༺❖༻ I am a developer with experience in working with Hugging Face pipelines and evaluating Large Language Models (LLMs). I see that you need a Jupyter notebook that follows your Moodle template. This notebook should be able to run on Colab and cover ways of summarising text using the XSum dataset. The notebook will have a pipeline that includes loading and splitting data preparing it for use selecting a model and evaluating its performance. I will use a Hugging Face model and evaluate it using ROUGE. The results will be easy to understand and reproduce. I will try out approaches to summarisation. These include zero-shot, shot and prompt-engineered summarisation. I will compare the results of these approaches in a table. I will also write a summary of my findings. This will include what worked well what didn't and how the results compare to what I expected. I will write this summary in a cell. The notebook will be well organised and easy to run. It will meet all your requirements, for the assignment. Lets talk soon. I want to confirm any requirements you have. I will then provide you with a notebook that you can submit away.

@sterlingl1

Hello! there, I'm Sterling, and I'd love to help you build a complete Jupyter notebook comparing LLM approaches for the XSum summarisation task. With over six years of experience, I specialize in AI, LLMs, and Hugging Face workflows. Project Understanding: You need a Colab-ready notebook using the EdinburghNLP/XSum dataset to evaluate zero-shot, few-shot, and prompt-engineered summarisation, including proper data splitting, evaluation metrics, and a final performance analysis. My Approach: Initial Analysis: Load and preprocess the dataset, define train/test split, and configure Hugging Face pipeline (lightweight model like FLAN-T5 or similar for Colab efficiency). Development: • Implement zero-shot summarisation on test set • Implement few-shot prompting with examples • Apply prompt engineering (constraints: length, style) • Evaluate using ROUGE (ROUGE-1, ROUGE-L) Review and Finalization: Generate comparison table, add markdown explanations, and write a concise 200-word analysis of results. Timeline: Ready to start immediately - delivery within 2–3 days. Experience: I’ve built multiple NLP notebooks using Hugging Face, including summarisation tasks with evaluation and prompt optimization. Budget: I can complete this for $180, including full notebook, outputs, and documentation. Looking forward to helping you achieve top marks. Best regards, Sterling

@shadabkhan92

As an experienced AI professional with a sharp focus on deploying LLMs into real-world production infrastructures, I am uniquely qualified to tackle your project. My team and I have deep expertise in utilizing cutting-edge techniques like zero-shot learning, few-shot learning, and prompt engineering — precisely the skills you need for comparing different approaches and improving summarization tasks using an LLM. Our proficiency has been demonstrated by designing and fine-tuning models with similar objectives as your project. Beyond our AI capabilities, we have proven strengths in providing comprehensive solutions that integrate seamlessly into existing systems. We're well-versed in important tools like Google Colab and popular libraries, ensuring fluid transition and continuity throughout the project life cycle.

@ruslanfulldev

As an AI specialist with a comprehensive understanding of Python-based tools and data automation, I am equipped with the necessary skills to tackle your Artificial Intelligence LLM project head-on. I have a deep knowledge of using models from Hugging Face, which is paramount for this task. Additionally, my proficiency in implementing zero-shot, few-shot learning, and prompt engineering approaches will ensure a robust evaluation for your project. In summary, my proven ability to fuse technology and business needs will be invaluable for your Artificial Intelligence LLM project. From generating swift yet reliable solutions to maintaining clear communication throughout the process, I offer everything your assignment demands. Given the opportunity to contribute to your project, I am ready to maximize my skills and experience for a satisfactory outcome. Let's get started!

@sergiom17

Hi there ✌️, You need a complete Jupyter Notebook (Colab-ready) following your Moodle template that evaluates an LLM on a text summarisation dataset using zero-shot, few-shot, and prompt engineering approaches, then compares results using proper evaluation metrics and provides a short analysis discussion. The final submission must include clean code, outputs, correct train/test handling, and a results table as required. I’ve worked on multiple NLP and LLM evaluation tasks involving Hugging Face datasets, including zero-shot and few-shot benchmarking, prompt engineering experiments, and fine-tuning transformer models in Google Colab. I’m comfortable setting up reproducible pipelines (data splitting, preprocessing functions, tokenizer setup, and trainer configuration) and ensuring everything runs smoothly within computational limits while producing clean, well-structured outputs for academic submission. I am ready to start immediately. I look forward to speaking with you.

@mojjammil

As an artificial intelligence expert with a deep understanding of the nuances of machine learning, I strongly believe I am the perfect fit for your artificial intelligence LLM project. I am well-versed in employing large language models for various tasks, especially on platforms such as Hugging Face. My prior work on fine-tuning models for similar tasks, evident from my extensive experience and expertise, can be a huge asset in effectively tackling your dataset. Specifically, I have substantial experience with zero-shot learning and few-shot learning, two critical components of your project. I can confidently assure you that I will meticulously evaluate model performance on the test dataset while implementing these approaches. Moreover, my proficiency in prompt engineering aligns perfectly with your final objective and will enable me to provide articulate instructions and constraints to achieve desirable summaries. Finally, my proven ability to assess and interpret model performances will greatly aid in step 5 of your project where a thoughtful discussion concerning the various aspects of result interpretation is required. With me on board, you can expect a seamless execution of the project on Google Colab keeping all your confidentiality concerns intact. I look forward to discussing this project further and demonstrating how my skills and experience can add tremendous value to its successful completion.

@zuoe1

Hello, This project is a strong match for my experience with NLP workflows, Hugging Face models, and Colab-based notebook development. I can prepare a clean Jupyter notebook following the Moodle template, covering data preparation, zero-shot, few-shot, and prompt-engineering approaches for XSum summarisation, with all outputs included and structured clearly for submission. I would keep the notebook practical and well documented, selecting a suitable model that balances summarisation quality with Colab constraints, then setting up preprocessing, evaluation on the test set only, and a clear comparison table for all four approaches. I can also write the final interpretation section in a concise academic style so the results, errors, and expectations are explained properly within the required word limit. Do you already know which Hugging Face model you want to use, or would you like the notebook built around the most reliable Colab-friendly option for this assignment?