Srikanta Prasad (Sri)
PRINCIPAL PRODUCT MANAGER
Srikanta (Sri) is working as a Principal product Manager, in OCI Data Science. He is leading efforts related to experiment tracking with oci-mlflow, OCI Data Science Feature Store and Model catalog capabilities in OCI Data Science portfolio. Sri brings about 19+ years of work experience working in Industry verticals such as Aviation and Aerospace, Semiconductor manufacturing and print and media verticals. He holds a Master’s Degree from National University of Singapore, MBA from University of North Carolina.
Recent Blogs
Unlocking AI potential: NVIDIA NIM on OCI
NVIDIA NIM is a set of easy to use microservices designed for secure, reliable deployment of high performance AI model inferencing across clouds, data centers, and workstations.
Deploy Falcon-7B with NVIDIA TensorRT-LLM on OCI
This blog details deploying the Falcon 7B Large Language Model on Oracle Cloud using Nvidia's TensorRT LLM framework. Falcon 7B/40B/180B, comparable to Google's PaLM 2 and GPT-4, is trained on 3.5 trillion tokens. The deployment, enhanced by NVIDIA's Triton Inference Server, leverages Oracle Cloud's robust infrastructure.
Enhancing OCI Data Science: Unveiling the New Autoscaling Feature for ...
Oracle Cloud Infrastructure (OCI) now enhances its model deployment capabilities with the introduction of autoscaling features, designed to dynamically adjust computing resources in real-time. This pivotal update offers seamless scalability, ensuring optimal performance and cost-efficiency for diverse computational demands in model deployment.
Optimizing Machine Learning Deployments on OCI: Introducing ...
Efficiently deploying machine learning models in the cloud involves navigating challenges like resource management and balancing cost and performance. This is particularly crucial for models with fluctuating computational demands. The introduction of burstable VMs and autoscaling for data science model deployment in OCI addresses these challenges by providing flexible resource allocation.
Generative AI Chatbot using LLaMA-2, Qdrant, RAG, LangChain & ...
This blog delves into creating an advanced chatbot using the LLaMA-2 model, Qdrant vector database, RAG framework, and LangChain, highlighting their integration in a user-friendly Streamlit web app.