Skip to content
View alishafique3's full-sized avatar
25 followers · 2 following

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

Block or report alishafique3

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
alishafique3/README.md

A passionate researcher in efficient machine learning design with a focus on large language models (text, vision), classical machine learning, mlops, and parallel computing.


🎓 Pursuing PhD in Electrical and Computer Engineering @ the Kansas State University.

📖 Graduate research assistant @ the ISCAAS Lab.

💻 Currently developing lightweight large language models using knowledge distillation.

🌱 Love to make research projects, tutorials, and insightful technical blogs. Personal website

⚡ Fun fact: I love to travel and attend various community festivals.

Technical Skills:

Connect with me:

Email LinkedIn Medium

Pinned Loading

  1. Finetuning_Of_LLM_On_Single_GPU_Using_QLoRA Finetuning_Of_LLM_On_Single_GPU_Using_QLoRA Public

    In this project, LLM (model: T5-3b) is finetuned on a single GPU for summarization task. Memory footprints of the model is reduced using PEFT technique called Quantized LoRA.

    Jupyter Notebook

  2. LLM-Evaluations-Hub LLM-Evaluations-Hub Public

    A repository that provides a thorough collection of approaches and methods used for evaluating Large Language Models (LLMs).

    Jupyter Notebook 2

  3. LLM-Prompt-Engineering-Techniques-and-Best-Practices LLM-Prompt-Engineering-Techniques-and-Best-Practices Public

    Prompt engineering is an essential skill for harnessing the full potential of large language models (LLMs). By carefully crafting prompts, you can guide these powerful AI systems to generate high-q…

    1

  4. Distributed_Training_of_LLM_Using_DeepSpeed Distributed_Training_of_LLM_Using_DeepSpeed Public

    In this project, LLM (model: distilbert) is finetuned on a multiple GPUs for text classification task. Distributed training is performed using deepspeed (ZeRO 1, 2, and 3) with profiling in wandb.

    Python 2

  5. PyTorch_Training_Optimization_with_Memory_Analysis PyTorch_Training_Optimization_with_Memory_Analysis Public

    In this project, training stage is optimized using memory analysis in Pytorch Tensorboard. Automatic mixed precision, increased batch size, reduced H2D copy, multiprocessing and pinned memory techn…

    Jupyter Notebook 1

  6. Efficient_Inference_Optimizations_and_Benchmarking Efficient_Inference_Optimizations_and_Benchmarking Public

    This project utilizes model optimization techniques such as pruning, clustering and quantization that enables efficient use of memory, less power consumption and make computations simple.

    Jupyter Notebook