Train AI models with Unsloth and Hugging Face Jobs for FREE

This org is for explorers of Unsloth + HF Jobs that want to receive free credis to try it out. The project was announced here and feedback is very much welcome here

You can use Unsloth and small models like LiquidAI/LFM2.5-1.2B-Instruct for fast LLM fine-tuning through coding agents like Claude Code and Codex. Unsloth provides ~2x faster training and ~60% less VRAM usage compared to standard methods, so training small models can cost just a few dollars.

Free HF Jobs Credits

We are giving away free credits to train the model on Hugging Face Jobs. Join the Unsloth Jobs Explorers to claim your free credits and pro subscription.

• A Hugging Face account (required for HF Jobs)
• Billing setup but you won't need to pay anything.
• A Hugging Face token with write permissions

Running Jobs With Unsloth

If you want to train a model using HF Jobs and Unsloth, you can simply use the hf jobs CLI to submit a job.

First, you need to install the hf CLI. You can do this by running the following command:

# mac or linux
curl -LsSf https://hf.co/cli/install.sh | bash

Next you can run the following command to submit a job:

hf jobs uv run https://huggingface.co/datasets/unsloth/jobs/resolve/main/sft-lfm2.5.py \
    --flavor a10g-small  \
    --secrets HF_TOKEN  \
    --timeout 4h \
    --dataset mlabonne/FineTome-100k \
    --num-epochs 1 \
    --eval-split 0.2 \
    --output-repo your-username/lfm-finetuned

Check out the training script and Hugging Face Jobs documentation for more details.