PinnedRam VegirajuAbout Me — Ram VegirajuMy Top Medium Stories — Subscribe Here & Join My Newsletter·2 min read·Apr 21, 2022--1--1
Ram VegirajuinTowards Data ScienceUsing Generative AI To Curate Date RecommendationsUtilizing Amazon Bedrock, Google Places, LangChain, and Streamlit·9 min read·Mar 21, 2024----
Ram VegirajuinAWS in Plain EnglishDeploying Transformers ONNX Models on Amazon SageMakerAchieve High Scale Performance Utilizing Triton Inference Server With SageMaker Real-Time Inference·8 min read·Mar 13, 2024----
Ram VegirajuinAWS in Plain EnglishBring Your Own LLM Evaluation Algorithms to SageMaker Clarify Foundation Model EvaluationsExtend the FMEval library to incorporate your own evaluations into MLOps workflows.·7 min read·Mar 12, 2024----
Ram VegirajuinAWS in Plain EnglishImage To Text With Claude 3 SonnetExploring The New Claude Model On Amazon Bedrock·5 min read·Mar 5, 2024--2--2
Ram VegirajuinTowards Data ScienceGenerate Music Recommendations Utilizing LangChain AgentsPowered by Bedrock Claude and the Spotify API·10 min read·Mar 5, 2024--1--1
Ram VegirajuinTowards Data ScienceOptimized Deployment of Mistral7B on Amazon SageMaker Real-Time InferenceUtilize large model inference containers powered by DJL Serving & Nvidia TensorRT·9 min read·Feb 21, 2024--1--1
Ram VegirajuinTowards Data ScienceAn Introduction To Fine-Tuning Pre-Trained Transformers ModelsSimplified utilizing the HuggingFace trainer object·5 min read·Feb 17, 2024----
Ram VegirajuinTowards Data ScienceBuilding a Multi-Purpose GenAI Powered ChatbotUtilize SageMaker Inference Components to work with Multiple LLMs Efficiently·10 min read·Feb 7, 2024--1--1
Ram VegirajuinTowards Data ScienceDeploying Large Language Models with SageMaker Asynchronous InferenceQueue Requests For Near Real-Time Based Applications·10 min read·Jan 27, 2024----