Daniel Han - Low Level Technicals of LLMs
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_163_5a77bb6f41.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_164_ef94585a79.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_165_dc6f465b21.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_168_c71ce62f9a.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_169_30138f9a5d.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_166_9e2620c5f0.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_167_e41a913f83.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_128_7658d5b1ec.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_129_63deff84b7.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_125_b4f75512ba.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_127_5d71e7938b.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_123_4d0d6a46b2.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_126_1f7dc7acdb.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_133_1990bab01d.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_131_afba6c46a2.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_134_d61e67e867.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_132_4377141fa9.jpg)
![](https://aie-cms-uploads.s3.us-west-1.amazonaws.com/AIE_Summit_2024_Day_1_WEB_124_e06784a08d.jpg)
Open Models: This workshop will be split into 3x one hour blocks:
It's recommended you have Python with Pytorch and Unsloth installed (or use online Google Colab / Kaggle). College level maths and programming would be helpful.
Hey I'm Daniel, the algos guy behind Unsloth. I love making LLM training go fast! We're the guys who fixed 8 of Google's Gemma bugs, a 2048 SWA Phi-3 issue, found tokenization issues and fixed untrained tokens with Llama-3, and I run Unsloth with my brother Michael!
Our open source package makes finetuning of LLMs 2x faster and uses 70% less VRAM with no accuracy degradation. I used to work at NVIDIA making GPU algos go fast and helped NASA engineers process data from a Mars rover faster!
Hey I'm Daniel, the algos guy behind Unsloth. I love making LLM training go fast! We're the guys who fixed 8 of Google's Gemma bugs, a 2048 SWA Phi-3 issue, found tokenization issues and fixed untrained tokens with Llama-3, and I run Unsloth with my brother Michael!
Our open source package makes finetuning of LLMs 2x faster and uses 70% less VRAM with no accuracy degradation. I used to work at NVIDIA making GPU algos go fast and helped NASA engineers process data from a Mars rover faster!
We have now sold out of Early Bird tickets; General Admission has also sold out.
Please join us online for the free livestream.