Course 04
LLM training
- Thursday, 14 January 2027
- 08:45 – 10:15
- On site
This session starts with how language models are trained: pretraining, the cost in compute and memory, distributed training and the main optimisations.
The second half covers finetuning, which the following lab builds on.
On the programme
- 01Pretraining
- 02Quantization
- 03Hardware optimization
- 04Supervised finetuning (SFT)
- 05Parameter-efficient finetuning (LoRA)