jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Refine readme of InstructionTuning (#1794)

Browse Source 
Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com>
This commit is contained in:
XinyuYe-Intel
2025-04-20 16:17:13 +08:00
committed by GitHub
parent 1eb2e36a18
commit bc168f1732
3 changed files with 24 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
InstructionTuning/README.md
View File

@@ -2,7 +2,17 @@
Instruction tuning is the process of further training LLMs on a dataset consisting of (instruction, output) pairs in a supervised fashion, which bridges the gap between the next-word prediction objective of LLMs and the users' objective of having LLMs adhere to human instructions. This implementation deploys a Ray cluster for the task.
## Deploy Instruction Tuning Service
# Table of contents
1. [Architecture](#Architecture)
2. [Deployment Options](#Deployment-Options)
3. [Instruction Tuning Service Usage](#Instruction-Tuning-Service-Usage)
## Architecture
The instruction tuning application is a customizable end-to-end workflow that takes user provided instruction dataset to finetune the user specified LLMs.
## Deployment Options
### Deploy Instruction Tuning Service on Xeon
@@ -12,7 +22,7 @@ Refer to the [Xeon Guide](./docker_compose/intel/cpu/xeon/README.md) for detail.
Refer to the [Gaudi Guide](./docker_compose/intel/hpu/gaudi/README.md) for detail.
## Consume Instruction Tuning Service
## Instruction Tuning Service Usage
### 1. Upload a training file

8
InstructionTuning/docker_compose/intel/cpu/xeon/README.md
View File

@@ -1,8 +1,12 @@
# Deploy Instruction Tuning Service on Xeon
# Deploy Instruction Tuning Service on Intel® Xeon® Processors
This document outlines the deployment process for a Instruction Tuning Service utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice on Intel Xeon server. The steps include Docker image creation, container deployment. We will publish the Docker images to Docker Hub, it will simplify the deployment process for this service.
## 🚀 Build Docker Images
# Table of contents
1. [Instruction Tuning Quick Start deployment](#Instruction-Tuning-Quick-Start-deployment)
## Instruction Tuning Quick Start deployment
First of all, you need to build Docker Images locally. This step can be ignored after the Docker images published to Docker hub.

8
InstructionTuning/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -1,8 +1,12 @@
# Deploy Instruction Tuning Service on Gaudi
# Deploy Instruction Tuning Service on Intel® Gaudi® Platform
This document outlines the deployment process for a Instruction Tuning Service utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice on Intel Gaudi server. The steps include Docker image creation, container deployment. We will publish the Docker images to Docker Hub, it will simplify the deployment process for this service.
## 🚀 Build Docker Images
# Table of contents
1. [Instruction Tuning Quick Start deployment](#Instruction-Tuning-Quick-Start-deployment)
## Instruction Tuning Quick Start deployment
First of all, you need to build Docker Images locally. This step can be ignored after the Docker images published to Docker hub.