New Show Hacker News story: Show HN: Finetune Llama-3.1 2x faster in a Colab

Show HN: Finetune Llama-3.1 2x faster in a Colab
1 by danielhanchen | 0 comments on Hacker News.
Just added Llama-3.1 support! Unsloth https://ift.tt/X62eL5V makes finetuning Llama, Mistral, Gemma & Phi 2x faster, and use 50 to 70% less VRAM with no accuracy degradation. There's a custom backprop engine which reduces actual FLOPs, and all kernels are written in OpenAI's Triton language to reduce data movement. Also have an 2x faster inference only notebook in a free Colab as well! https://ift.tt/zHyn5Cq...

إرسال تعليق

أحدث أقدم

نموذج الاتصال

How To Get It For Free?

If you want to get this Premium Blogger Template for free, simply click on below links. All our resources are free for skill development, we don't sell anything. Thanks in advance for being with us.