Pinned Repositories
aws-sagemaker-chatbot-memory
Build a context-aware chatbot with short and long-term memory using AWS SageMaker and other AWS services for improved user interactions.
ChatGPT-Decoded-GPT2-FAQ-Bot-RLHF-PPO
A Practical Guide to Developing a Reliable FAQ Chatbot with Reinforcement Learning and Human Feedback using GPT-2 on AWS
knowledge-augmented-LLMs
Context is Key: Combining Embedding-based Retrieval with LLMs for Comprehensive Knowledge Enrichment
multi-turn-chatbot-gpt-sagemaker
Multi-Turn Chatbot with GPT-Neo and SageMaker: A conversational AI system for engaging and informative interactions with users.
no-code-low-code
No Code Low Code Examples
sagemaker-jumpstart-generative-ai-examples
Unlocking Creativity: Generative AI with SageMaker Jumpstart
SageMaker-Load-Testing
SageMaker Load Testing using Locust
SageMaker-Studio-Examples
End to End SageMaker Example Notebooks
train-bert-from-scratch-on-sagemaker
Pretraining a large language model from scratch with your own custom domain data and Amazon SageMaker
train-gpt-from-scratch-on-sagemaker
Pretraining a GPT from scratch with your own custom domain data and Amazon SageMaker
arunprsh's Repositories
arunprsh/sagemaker-jumpstart-generative-ai-examples
Unlocking Creativity: Generative AI with SageMaker Jumpstart
arunprsh/knowledge-augmented-LLMs
Context is Key: Combining Embedding-based Retrieval with LLMs for Comprehensive Knowledge Enrichment
arunprsh/no-code-low-code
No Code Low Code Examples
arunprsh/aws-sagemaker-chatbot-memory
Build a context-aware chatbot with short and long-term memory using AWS SageMaker and other AWS services for improved user interactions.
arunprsh/ChatGPT-Decoded-GPT2-FAQ-Bot-RLHF-PPO
A Practical Guide to Developing a Reliable FAQ Chatbot with Reinforcement Learning and Human Feedback using GPT-2 on AWS
arunprsh/multi-turn-chatbot-gpt-sagemaker
Multi-Turn Chatbot with GPT-Neo and SageMaker: A conversational AI system for engaging and informative interactions with users.
arunprsh/train-bert-from-scratch-on-sagemaker
Pretraining a large language model from scratch with your own custom domain data and Amazon SageMaker
arunprsh/train-gpt-from-scratch-on-sagemaker
Pretraining a GPT from scratch with your own custom domain data and Amazon SageMaker
arunprsh/SageMaker-Studio-Examples
End to End SageMaker Example Notebooks
arunprsh/gpt-prompt-engineer
arunprsh/AWS-ML-Pipelines
Collection of AWS code samples for ML Workflow creation and orchestration
arunprsh/flask-protobuf-sagemaker-demo
Invoke Sagemaker MXNet endpoint from a Docker container
arunprsh/lambda-collection
Collection of AWS Lambda related assets
arunprsh/learn-cantrill-io-labs
Standard and Advanced Demos for learn.cantrill.io courses
arunprsh/Prompt-Engineering-Guide
:octopus: Guides, papers, and resources for prompt engineering
arunprsh/SageMaker-Data-Wrangler-L400-Workshop
SageMaker Data-Wrangler L400 Workshop
arunprsh/amazon-sagemaker-predict-training-resource-usage
arunprsh/autopilot-batch
Example notebooks demonstrating how to make batch predictions with SageMaker Autopilot
arunprsh/aws-cross-account-inference
Invoke a Sagemaker Endpoint in another AWS account from an app (or notebook instance) that is in a private VPC (no internet) using cross-account assume role and private link
arunprsh/aws-saas-factory-eks-reference-architecture
arunprsh/feature-encoders
Data Wrangler Feature Encoders
arunprsh/illustrated-machine-learning.github.io
Website containing illustrations about Machine Learning theory!
arunprsh/mlops-for-low-code-sagemaker
MLOps for Low-code ML with Amazon SageMaker
arunprsh/MLR402-reMARS-workshop
arunprsh/reinvent-2022-low-code-demos
AWS re:Invent 2022 Low-Code demos
arunprsh/sagemaker-studio-docker-ui-extension
Sagemaker Studio Docker UI Extension
arunprsh/sdocker
Helper application to automate setting up `local mode` and `docker` for SageMaker Studio
arunprsh/system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
arunprsh/Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
arunprsh/tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.