Templates / Unsloth Fine-tuning
CUDA 12.8SSHJupyterFine-tuning
Unsloth Fine-tuning
Fast, memory-efficient LoRA / QLoRA fine-tuning for Llama, Qwen, Gemma and more, driven from JupyterLab.
What's inside
- ✓PyTorch base + unsloth, trl, peft, bitsandbytes, datasets
- ✓Example script /workspace/examples/finetune_lora.py
How you connect
| Access | Where | Auth |
|---|---|---|
| SSH (root) | ssh -p <port> root@clearlayer.ca | Your SSH key |
| JupyterLab | https://r<id>-<random>.gpu.clearlayer.ca | Token in the link |
Quick start
SSH
ssh -p 20012 root@clearlayer.ca python /workspace/examples/finetune_lora.py # LoRA fine-tune of a small Qwen model