Ananda Rimal
Machine Learning Engineer | Learning Advanced ML & AI Agents
This profile was put together from Ananda's public GitHub portfolio, and they haven't joined Vibetown yet, so reach them through their portfolio. Is this you? Contact us to update or remove it.
About
Ananda Rimal works in ML & data science and AI engineering, based in Nepal. Machine Learning Engineer | Learning Advanced ML & AI Agents. Public projects on GitHub include LLM-Linguistic-adaptation-Romanized-Nepali-Research- (Benchmarking and fine-tuning of Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B for Romanized Nepali using a 10K…), Deerwalk-Teaching-Datascience (Comprehensive Data Science course repository containing lecture slides, notebooks, code examples, and…) and Gpt2-from-scratch-workshop (Build GPT-2 from first principles with core mathematics, Transformer architecture, attention, embeddings,…), mostly written in Jupyter and TypeScript.
Projects 6
- github.com
LLM-Linguistic-adaptation-Romanized-Nepali-Research-
Benchmarking and fine-tuning of Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B for Romanized Nepali using a 10K bilingual dataset, evaluating zero-shot vs QLoRA-based adaptation across multiple linguistic metrics.
- github.com
Deerwalk-Teaching-Datascience
Comprehensive Data Science course repository containing lecture slides, notebooks, code examples, and hands-on projects covering Data Analysis, Statistics, Mathematics for Machine Learning, Machine Learning, Deep Learning, NLP, and Retrieval-Augmented Generation (RAG).
- github.com
Gpt2-from-scratch-workshop
Build GPT-2 from first principles with core mathematics, Transformer architecture, attention, embeddings, training, and a complete PyTorch implementation from scratch. Workshop conducted by Ananda Rimal.
- github.com
Pytorch Workshop For Researcher
This workshop is conducted by Ananda Rimal, focusing on research-oriented deep learning and the core fundamentals of PyTorch, including tensor operations, automatic differentiation, neural network implementation, model training, and practical research applications.
- github.com
Jev Masterclass
Exploring JEV by TypeSafe AI — a System One Model designed for fast, structured decision-making with choices, scores, probabilities, and confidence values.
- github.com
Llm Fine Tuning Workshop
This is a resource for the workshop conducted by Ananda Rimal for AI developers and researchers, covering how LLM fine-tuning works, how LLMs are adapted to low-resource languages, and which fine-tuning and parameter-efficient adaptation techniques are most effective.