← Skill graph
Supervised fine-tuning
Part of Fine-tuning and post-training
Helps first
Nothing recommended beyond what is required.
Where it is assessed
7 assessed items, 0 done.
- AIE-205 M2.3 Run a supervised fine-tune · tier 1
- AIE-205 M2.4 The prompted baseline that has to lose first · tier 2
- AIE-205 M2.6 Retention: SFT mechanics and loss masking · tier 1
- AIE-205 M3.4 Where the low-rank assumption runs out · tier 2
- AIE-205 M5.1 Regression sweep on what you did not intend to change · tier 2
- AIE-205 M5.2 fine-tune-study, published · tier 3
- AIE-205 M5.4 Oral defense · tier 4
Verified sources
- AI Engineering
- Build a Large Language Model (From Scratch)
- Introduction - Hugging Face NLP Course
- Deep Dive into LLMs like ChatGPT · Andrej Karpathy
- Intro to Large Language Models · Andrej Karpathy
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- huggingface/transformers
- Stanford CS336 Language Modeling from Scratch I 2025 · Stanford Online