Setup and installation of LLaMa Factory on Azure

This section describes how to launch and connect to ‘Custom LLMs, Ready in Minutes with LLaMa Factory’ VM solution on Azure Platform.

1. Open Custom LLMs, Ready in Minutes with LLaMa Factory VM listing on Azure Marketplace.

2. Click on Get It Now

• Login with your credentials, provide the details here. Once done click on Get it now button at the bottom.

• It will take you to the Product details page. Click on Create.

• Select a Resource group for your virtual machine

• Select a Region where you want to launch the VM(such as East US)

• Note: If you see “This image is not compatible with selected security type. To keep trusted launch virtual machines, select a compatible image. Otherwise change your security type back to Standard” error message below the Image name as shown in the screenshot below then please change the Security type to Standard.

• Optionally change the number of cores and amount of memory.

Minimum VM Specs : 4GB vCPU / 16GB RAM. However fine tuning with this config will take much time. For swift performance please go with the 8GB vCPU/32GB RAM

Please note that the VM can also be deployed using NVIDIA GPU instance to fine tune models faster. Please check Publisher recommendations instance type for GPU (Standard_NC4as_T4_v3 - 4 vcpus, 28 GiB memory) or check the available NVIDIA GPU instances on Azure documentation page.

Select the Authentication type as Password and enter Username as ubuntu and Password of your choice.

• Optionally change the OS disk size and its type. By default the VM comes with 60GB of disk.

• Optionally change the network and subnetwork names. Be sure that whichever network you specify has ports 22 (for ssh), 3389 (for RDP) and 443 (for HTTPS) exposed.

The VM comes with the preconfigured NSG rules. You can check them by clicking on Create New option available under the security group option.

• Optionally go to the Management, Advanced and Tags tabs for any advance settings you want for the VM.
• Click on Review + create and then click on Create when you are done.
  Virtual Machine will begin deploying.

3. A summary page displays when the virtual machine is successfully created. Click on Go to resource link to go to the resource page. It will open an overview page of virtual machine.

4. If you want to update your password then open up the left navigation pane, select Run command, select RunShellScript and enter following command to change the password of the vm .

sudo echo ubuntu:yourpassword | chpasswd

Now the password for ubuntu user is set, you can SSH to the VM. To do so, first note the public IP address of the VM from VM details page as highlighted below

Open putty, paste the IP address and click on Open.

login as ubuntu and provide the password for ‘ubuntu’ user.

5. You can also connect to the VM’s desktop environment from any local windows machine using RDP protocol or local linux machine using Remmina.

6. To connect using RDP via Windows Machine, first note the public IP address of the VM from VM details page as highlighted below

7. Then From your local windows machine, goto “start” menu, in the search box type and select “Remote desktop connection”.
   In the “Remote Desktop connection” wizard, copy the public IP address and click connect

8. This will connect you to the VM’s desktop environment. Provide the username (e.g “ubuntu”) and the password set in the step4 to authenticate. Click OK

9. Now you are connected to the out of box “Custom LLMs, Ready in Minutes with LLaMa Factory” VM’s desktop environment via Windows Machine.

10. To connect using RDP via Linux machine, first note the external IP of the VM from VM details page, then from your local Linux machine, goto menu, in the search box type and select “Remmina”.

Note: If you don’t have Remmina installed on your Linux machine, first Install Remmina as per your linux distribution.

11. In the “Remmina Remote Desktop Client” wizard, select the RDP option from dropdown and paste the external ip and click enter.

12. This will connect you to the VM’s desktop environment. Provide “ubuntu” as the userid and the password set in above reset password step to authenticate. Click OK

13. Now you are connected to out of box “Custom LLMs, Ready in Minutes with LLaMa Factory” VM’s desktop environment via Linux machine.

14. The VM will generate a random password to login to LLaMa Factory Web Interface. To get the password, connect via SSH terminal as shown in above steps and run below command.

cat llama-factory-passwd.txt

Here username is admin with random password.

15. To access the Llama Factory Web Interface, copy the public IP address of the VM and paste it in your local browser as https://public_ip_of_vm. Make sure to use https and not http.

Browser will display a SSL certificate warning message. Accept the certificate warning and Continue.

16. Provide the ‘admin’ user and its password we got at step 14 above.

17. Now you are logged in to LLaMa Factory Web Interface. Here you can select different values and train/chat/evaluate the models.

Note: If you using CPU instance type then make sure to change the default value of Compute Type from bf16 to fp16 or fp32. If Training starts with the default value bf16 on CPU instance then it will show an error message “Your setup doesn’t support bf16/gpu.”

18. To begin with , you can set below values in Web Interface and click on Start to start the training. Once the training finishes, you can use the trained model for Chat.

Model name: Qwen2.5-3B-Instruct

Hub name: huggingface

Finetuning method: LoRA

Dataset: identity, alpaca_en_demo

Compute type: fp16 (for cpu instace) / bf16 (for gpu instance)

Output dir: train_qwen2 (Any name of your choice)

19. To access the LLaMa Factory CLI on this VM, connect via SSH terminal and run below command. This command will login you to LLaMa Factory container.

sudo docker exec -it llamafactory /bin/bash

20. If above command fails then please check the status of running container using :

sudo docker ps -a

If you see the container is not running and in Exited state then restart it with

sudo docker start llamafactory

21. Inside container you can run various llamafactory-cli commands or you can use lmf as a shortcut for llamafactory-cli.

For more details, please visit Official Documentation page