Link missing for Hyper-parameter tutorial | Unsloth AI | Page 1

fresh barn Aug 14, 2025, 12:18 PM

#

Hi,

Below is the link:

The link to 70B LLaMA fits in <48GB VRAM with QLoRA in Unsloth is missing.

Regards,

Optimal lora rank. alpha, number of epochs, batch size & gradient accumulation, QLoRA vs LoRA, target modules and more!

limpid bone Aug 15, 2025, 11:46 AM

#

Hi thank u for this

#

will update

#

Unsloth - Open source Fine-tuning & RL for LLMs

Fine-tune Meta's Llama 3.3 (70B) model which has better performance than GPT 4o, open-source 2x faster via Unsloth! Beginner friendly.

Now with Apple's Cut Cross Entropy algorithm.

fresh barn Aug 16, 2025, 7:54 AM

#

Now it does. When i was trying it yesterday it did not.

limpid bone Aug 16, 2025, 12:23 PM

#

oh weird ok let me know if the website errors out again

#Link missing for Hyper-parameter tutorial