Hi👋 I’M Ahmed a science computer engineer with 10 years of experience in the healthcare field. with all my knowledge helping businesses integrate new technologies especially LLM’s into their systems, I would be happy to share with you lessons on:
How language models works from the ground up (tokenization, embedding, pretraining to finetuning and inference).
How to adapt LLM’s to specific use case through prompt engineering or finetuning.
Explore different finetuning and quantization techniques such as PEFT LoRA and QLoRA.
Share insights on how to deploy models to cloud (GCP,AWS,AZURE) or locally (GGML,GGFU,GPTQ).
Share different projects (chatbots and systems) using RAG (Retrieval Augmented Generation), external API, Function Calls, through tools such as LangChain, HuggingFace, transformers etc.
LLMOps with Mlflow, cost efficient deployment using vLLM and Skypilot.
Let’s Connect:
I’m excited to engage with fellow tech enthusiasts, and anyone captivated by the potential of LLMs and generative AI. Don’t hesitate to get in touch, whether you have questions, topic suggestions, or simply want to exchange ideas over a virtual cup of coffee.