> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nebius.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Fine-tuning a large language model by using a Serverless AI job and Axolotl
You can use Serverless AI jobs to work with AI models and perform such operations as fine-tuning, scientific simulations, data processing or batch inference.
The example below demonstrates how to fine-tune the [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) large language model (LLM) with the support of the Low-Rank Adaptation (LoRA). This example also includes [Axolotl](https://axolotl.ai), an open-source tool for fine-tuning. Axolotl provides a [public container image](https://hub.docker.com/r/axolotlai/axolotl), which you deploy in a job and, as a result, run fine-tuning.
For a quick walkthrough of the web console workflow, watch the video below. If you prefer other interfaces or written instructions, follow the steps further down.
## Costs
Nebius AI Cloud charges you for the following billing items:
* [Compute virtual machines](/compute/resources/pricing#virtual-machines-gpus-vcpus-ram) (VMs)
* [Boot disks](/compute/resources/pricing#disks) attached to the VMs
* Used space in Standard storage in an [Object Storage bucket](/object-storage/resources/pricing#storing-data)
## Prerequisites
Make sure you are in a [group](/iam/authorization/groups/index) that has at least the `editor` role within your tenant or project; for example, the default `editors` group. You can check this in the [Administration → IAM](https://console.nebius.com/iam) section of the web console.
1. Make sure you are in a [group](/iam/authorization/groups/index) that has at least the `editor` role within your tenant or project; for example, the default `editors` group. You can check this in the [Administration → IAM](https://console.nebius.com/iam) section of the web console.
2. Install and configure the Nebius AI Cloud CLI and the AWS CLI. Here are the instructions, depending on what tools you have already installed:
* [How to install both CLIs](/object-storage/quickstart#prepare-your-environment)
* [How to install the Nebius AI Cloud CLI only](/cli/install)
* How to [install](https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html#getting-started-install-instructions) and [configure](/object-storage/interfaces/aws-cli#configuring-aws-cli) the AWS CLI only
## Steps
### Prepare an Object Storage bucket
To store job results, mount an [Object Storage bucket](/object-storage/overview#buckets) to your job. Serverless AI deletes the job after its completion. Thus, the bucket preserves the job data: checkpoints and LoRA adapter weights of a fine-tuned model.
For visual guidance on creating a bucket and uploading objects in the web console, watch the video below. If you prefer other interfaces or written instructions, follow the steps further down.
1. Create a bucket:
1. In the [web console](https://console.nebius.com), go to **Storage** → **Object Storage**.
2. Click **Create bucket**.
3. Specify the `fine-tuning-axolotl` name for the bucket.
4. In the **Maximum size** field, select **Unlimited**.
Leave the other settings at their default values.
5. Click **Create bucket**.
```bash theme={null}
nebius storage bucket create --name fine-tuning-axolotl
```
2. Save the `config.yaml` file specified below. It is required for Axolotl to run fine-tuning.
```yaml theme={null}
base_model: Qwen/Qwen2.5-0.5B
load_in_4bit: true
adapter: qlora
datasets:
- path: Salesforce/wikitext
name: wikitext-2-raw-v1
split: "train[:2000]"
type: completion
field: text
sequence_len: 128
micro_batch_size: 1
gradient_accumulation_steps: 1
learning_rate: 2e-4
max_steps: 30
val_set_size: 0
logging_steps: 5
output_dir: /workspace/output
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj
```
3. Upload this configuration file to the bucket:
1. In the web console, go to **Storage** → **Object Storage**.
2. Open the page of the `fine-tuning-axolotl` bucket.
3. Click **Add** → **Object**.
4. Upload the `config.yaml` file.
```bash theme={null}
aws s3 cp config.yaml s3://fine-tuning-axolotl/config.yaml
```
The file is stored in the `fine-tuning-axolotl` bucket as the `config.yaml` object.
Run this command in the directory where `config.yaml` is stored. Alternatively, specify an actual path to the file after `cp`.
### Run a fine-tuning job
Create a job that performs the following actions:
1. Runs an Axolotl container.
2. Mounts the bucket with the prepared configuration file in the read-write mode.
3. Executes fine-tuning.
4. Saves the fine-tuning results to the bucket.
To create and run such a job:
1. In the web console, go to **Serverless AI** → **Jobs**.
2. Click **Create job**.
3. On the page that opens, specify the following job settings:
* **Name**: `fine-tuning-axolotl-qwen-lora`.
* **Image path**: `docker.io/axolotlai/axolotl:main-20260309-py3.11-cu128-2.9.1`.
* **Entrypoint command**:
```bash theme={null}
bash -c "RUN_ID=run-$(date +%Y%m%d-%H%M%S); axolotl train /workspace/data/config.yaml && mkdir -p /workspace/data/output/$RUN_ID && cp -r /workspace/output/. /workspace/data/output/$RUN_ID"
```
* **Computing resources**: With GPU.
* **Available platform**: NVIDIA® L40S PCIe with Intel Ice Lake.
* **Preset**: 1 GPU — 8 CPUs — 32 GiB RAM.
* **Container disk, Size GiB**: 450.
* **Mount volumes**: Bucket.
* **Mount path**: `/workspace/data`. After that, click **Attach bucket** and then select the `fine-tuning-axolotl` bucket.
4. Click **Create**.
Run the following command:
```bash theme={null}
nebius ai job create \
--name "fine-tuning-axolotl-qwen-lora" \
--subnet-id "" \
--image docker.io/axolotlai/axolotl:main-20260309-py3.11-cu128-2.9.1 \
--platform gpu-l40s-a \
--preset 1gpu-8vcpu-32gb \
--disk-size 450Gi \
--volume ":/workspace/data" \
--container-command bash \
--args '-c "RUN_ID=run-$(date +%Y%m%d-%H%M%S); axolotl train /workspace/data/config.yaml && mkdir -p /workspace/data/output/$RUN_ID && cp -r /workspace/output/. /workspace/data/output/$RUN_ID"'
```
The command contains the following parameters:
* `--name`: Job name.
* `--subnet-id`: [Subnet ID](/vpc/networking/resources#how-to-get-a-subnet-id).
* `--image`: Container image to run. In the given example, the [public Axolotl container image](https://hub.docker.com/r/axolotlai/axolotl) is used.
* `--platform`: Virtual machine (VM) platform for the job. As Serverless AI jobs are based on [container VMs](/compute/virtual-machines/containers) in Compute, every job uses [Compute platforms and presets](/compute/virtual-machines/types).
* `--preset`: Number of GPUs, vCPUs and RAM allocated to the container. The preset must match the selected platform.
* `--disk-size`: Size of the job container disk.
* `--volume`: Volume to mount to the job container. Specify the ID of the `fine-tuning-axolotl` bucket created earlier. The bucket is used to store the job results and checkpoints.
To get the bucket ID, run `nebius storage bucket get-by-name --name fine-tuning-axolotl`.
* `--container-command`: Entrypoint command for the job container.
* `--args`: Arguments for `docker run` to pass to the entrypoint command.
The job takes several minutes to complete.
### Check the job results
1. View information about the job:
In the web console, go to **Serverless AI** → **Jobs** and then open the page of the `fine-tuning-axolotl-qwen-lora` job. It contains information about the job state and configuration.
```bash theme={null}
nebius ai job get
```
The command output shows the job state and configuration.
To get the job ID, run `nebius ai job get-by-name --name fine-tuning-axolotl-qwen-lora`.
2. Download LoRA adapter weights of the fine-tuning job. They are stored as files in the `output` directory, in the `fine-tuning-axolotl` bucket. To check these files, open the page of the `fine-tuning-axolotl` bucket in the [web console](https://console.nebius.com/).
To download a file, in its line, click → **Download**.
Command example for downloading a file:
```bash theme={null}
aws s3 cp s3://fine-tuning-axolotl/output/run-20260309-160510/checkpoint-30/adapter_config.json download/output/run-20260309-160510/checkpoint-30/adapter_config.json
```
In this example, the `s3://...` path points to the file in the bucket, and the `download/...` path points to a local `download` directory.
## How to delete the created resources
Used space in the created bucket is chargeable. If you don't need it, [delete the bucket](/object-storage/buckets/manage#how-to-delete-buckets), so Nebius AI Cloud doesn't charge for it.
## See also
* [Axolotl quickstart](https://docs.axolotl.ai/docs/getting-started.html)
* [Example: Fine-Tune Qwen3 14B with Axolotl](https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html)
* [Axolotl GitHub repository](https://github.com/axolotl-ai-cloud/axolotl)