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…

Introduction consume LLama2 Code model in Azure ML Using Azure ML Using NVidia A100 GPU SKU Standard_NC48ads_A100_v4 (48 cores, 440 GB RAM, 128 GB disk) I had to request quota increase using Azure ML to achieve this experiment. using open-source data set Following this experiment from here Idea here is show…

Introduction Segment anything with ONNX Runtime using Azure Machine Learning Using Azure ML Using NVdia A100 GPU SKU NCADSA100v4 I had to request quota increase using Azure ML to achieve this experiment Using meta’s model and samples Idea here is show how it can run in Azure Machine learning Original code…

Introduction Fine tune TRL model in Azure ML Using Azure ML Using NVidia A100 GPU SKU NCADSA100v4 I had to request quota increase using Azure ML to achieve this experiment using open source data set Following this experiment from here Tune GPT2 to generate positive reviews Code First install necesary packages %load_ext…

Introduction Fine tune LLama2 model in Azure ML Using Azure ML Using NVdia A100 GPU SKU NCADSA100v4 I had to request quota increase using Azure ML to achieve this experiment using open source data set Following this experiment from here Code First install necesary packages !pip install -U pip !pip install accelerate==0.18.0 !pip install…

Introduction Build Large Language Models using Prompt Flow in Azure ML Using Prompt Flow Using Azure Cognitive search vector services using Azure open ai service Concept First create a vector store and provide cognitive search service Create a connections to open ai and also cognitive search Create a prompt flow Create a…

Introduction Build Large Language Models using Prompt Flow in Azure ML Using Prompt Flow Using Azure Cognitive search vector services using Azure open ai service Concept First create a vector store and provide cognitive search service Create a connections to open ai and also cognitive search Create a prompt flow Create a…

Steps Download whisper V2 large model Create a conda.yaml file for the environment create a score file for the endpoint Deploy it as managed endpoint Sample audio file to test the endpoint Score file import os import logging import json import numpy from typing import Dict from transformers.pipelines.audio_utils …

Overview Use Azure Cognitive Search to store and retrieve vectors from a vector store using langchain use open ai embeddings to create a vector Prerequisites Azure Account Azure Cognitive Search Azure Open AI Azure Storage Account Code install langchain pip install --upgrade langchain pip install --index-url=https://pkgs.dev.azure.com/azure-sdk/public/_packaging/azure-sdk-for-python/pypi/simple/ azure-search-documents==11.4.0a20230509004 pip install azure-identity pip install pypdf