[go: up one dir, main page]
Skip to content
View Cenrax's full-sized avatar
17 followers · 46 following
  • HTCD

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Block or report Cenrax

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
Cenrax/README.md

Hi there 👋

Welcome to my Profile

  • I’m currently working as Principal AI Engineer focused mainly on building scalable AI solution.
  • My expertise is in building production grade AI products.
  • My research and innovations comprises of making LLMs compute efficient and using creating low-latency inference stack.
  • I am also working on the reliability and security of LLMs' and deployed various guardrails to make LLMs more secure.
  • Applied Machine Learning, Statistics and NLP is something in which I keep myself updated.
  • 📫 How to reach me: https://www.linkedin.com/in/subham-kundu-2746b515b/

Welcome to my Profile.

I have completed my bachelor's in Electronics and Communication Engineering from the Institute of Engineering and Management, Kolkata. I believe in continuous learning and try to find out real-life applications of whatever knowledge I have gained. I love to read scientific articles and try to keep myself updated with the latest technologies that is flourishing around the world.

I love to read books and gain insights and ideas into various domains from hardware to software.

I am a great fan of parallel processing and optimizing stuffs and I always try to explore and create application which can be made with limited power resources or I can say an application which can be cumulatively built.

Pinned

  1. FineTuningLlama2 FineTuningLlama2 Public

    This is a repository where I have fine-tuned an Llama2 on an open source dataset from Kaggle.

    Jupyter Notebook

  2. AutoscalingKubernetes-HandleHeavyTraffice AutoscalingKubernetes-HandleHeavyTraffice Public

    This is an demo project for autoscaling an app deployed in Kubernetes using nginx Ingress Controller and heavy traffic is simuated using locust

    2

  3. LLMSummaEvaluation LLMSummaEvaluation Public

    This project is meant for evaluating the summarization capabilities of three Large Language Models (T5-Small, T5-Large and GPT2). The dataset used in CNN_Daily Mail dataset

    Jupyter Notebook 2

  4. AKS_KVS_ETCD AKS_KVS_ETCD Public

    Install an Scalable ETCD database in Azure Kubernetes Service

    Python

  5. TransformerFromScratch TransformerFromScratch Public

    This is an implementation of transformer for translating english to italian from scratch in pytorch

    Python

  6. 5GHackathon 5GHackathon Public

    This is the software stack for low-latency real-time video inferencing in a edge server

    JavaScript 1