Abraham Tesfaye

AI/ML Engineer | Software Engineer

Enthusiastic programmer with a strong foundation in machine learning and a passion for generative AI. Eager to learn and apply my skills to fine tune LLMs, build chatbots & RAG pipelines, craft and engineer prompts, and generate AI images while making use of deep learning techniques to create. Proficient in Python, Langchain and LLama with experience in machine learning libraries and skilled in NLP and image processing. Excited to contribute to cutting-edge AI and ML projects and push the boundaries of what's possible.


Interests: Artificial Intelligence, Machine Learning, Data Science, Computer Vision, NLP, Documentaries, Traveling


Projects

LLM Fine Tuning: Generating Amharic Creatives 2024

Fine-tuning a Large Language Model (LLM) on Amharic text data to ensure high-quality text embedding and generation and incorporating a Retrieval-Augmented Generation (RAG) pipeline

Fine-Tuning LLM QloRA Data Labling Specific Learning RAG

Read More
Precision RAG: Enterprise Grade 2024

By automating prompt generation, testing, and ranking, LLMs are made more accessible, efficient, and effective across various industries.

RAG Prompt Engineering ChatGPT RAGAS

Read More
Semantic Image and Text Alignment: Storyboard Synthesis 2024

Automates storyboard generation for mobile ad campaigns from text descriptions.

Machine Learning NLP Computer Vision

Read More
Redash Chatbot Add-on 2024

Integrates a chat add-on for Redash that uses natural language processing to unlock business intelligence.

Chatbot Redash Postgres OpenAI NLP

Read More

Essays

Semantic Image and Text Alignment: Storyboard Synthesis

17 Feb 2024

Introduction In this transformative era of advertising and recognizing the potential for technology to streamline and enhance the ad creation process, Adludio is embarking on an ambitious initiative to automate the end-to-end process of advertising production. Adludio is a well...

CV NLP ML

LLM Fine-Tuning : Generate Amharic Creatives

04 Feb 2024

Introduction Fine-Tuning Mistral 7B to Enable Quality Embedding and Text Generation for Amharic Language Given Telegram’s growing prominence as a messaging platform, AiQEM (an African startup focused on AI and Blockchain business solutions) needs to adjust its advertising strategy to...

Fine-Tuning Mistral 7B Amharic Ads

Precision RAG: Enterprise Grade

08 Jan 2024

Prompt Tuning For Building Enterprise Grade RAG Systems Introduction RAG stands for Retrieval-Augmented Generation, which is a powerful and flexible method for retrieving and generating natural language with large language models. It consists of Retrieval-based approaches that use a large...

RAG Prompt Engineering RAGAS Evaluation