Use Case Show case how to consume semantic kernel in Azure Machine Learning Notebook Using python sdk Use huggingface models Add memory to the model Code First install semantic kernel %pip install --upgrade semantic-kernel %pip install torch==2.0.0 %pip install transformers==4.28.1 %pip install sentence-transformers==2.2.2 %pip install accelerate Restart the kernel Load Environment variable from…

Use Case Show case how to consume semantic kernel in Azure Machine Learning Notebook Using python sdk Code First install semantic kernel %pip install --upgrade semantic-kernel Restart the kernel Load Environment variable from dotenv import dotenv_values # specify the name of the .env file name env_name = "env.env" # change to use your own…

Introduction Design HA and DR architecture for LLM application Inside same region Across regions Across globally Using Azure Open AI Using App service for semantic kernel or web application Using Azure Cognitive Search for Vector Index. Implementing RAG — Retrieval Augumented Generation Architecture is high level and not detailed Architecture Architecture — Explained Azure Open…

Goal Run sample fine tuning from Azure Machine learning Using SDK Using Azure Open AI GPT 3.5-Turbo Using sample data set Using sample code — https://learn.microsoft.com/en-us/azure/ai-services/openai/tutorials/fine-tune?tabs=command-line from above code create the training and valdiation jsonl files locally to use for below code Code install libraries %pip install openai %pip install json %pip…

Using GPU compute to fine tune llama2 and using deepspeed to parallelize the fine tuning introduction Fine tune large language — Llama2 models in Azure ML Using GPU Clusters Using existing samples from our Azure machine learning sdk examples I had to request quota increase using Azure ML to achieve this experiment using open source data set Summarization url : https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/system/finetune/Llama-notebooks/text-generation/summarization_with_text_gen.ipynb

Azure Machine learning consuming azureopen ai whisper model Introduction Using Azure open ai whisper model in Azure ML Using Azure Machine Learning notebook Using Pythin Code Using Azure Open AI Whisper model Deployment name: whisper Model name: whisper Code Upgrade your open ai sdk to latest version %pip install --upgrade openai import Azure open ai configuration from dotenv import dotenv_values #…

How to process embedding for large rows of data with single api within limit This is a sample notebook to process embedding for large rows of data with single api within limit Ada 2 will have a limit of 30 rows within few seconds to process. This sample process 30 rows at a time and wait for 7 seconds to avoid throttling Some libraries…

Using GPU compute to fine tune large language models and using deepspeed to parallelize the fine tuning introduction Fine tune large language models in Azure ML Using GPU Clusters Using existing samples from our Azure machine learning sdk examples I had to request quota increase using Azure ML to achieve this experiment using open source data set Summarization url : https://github.com/Azure/azureml-examples/blob/main/sdk/python/foundation-models/system/finetune/summarization/news-summary.ipynb

Using GPU compute to fine tune large language models introduction Fine tune large language models in Azure ML Using GPU Clusters Using existing samples from our Azure machine learning sdk examples Using SKU — STANDARD_NC64AS_T4_V3 I had to request quota increase using Azure ML to achieve this experiment using open source data set Here is the GPU details from url…