AlphaUncommon
therealoliver/Deepdive-llama3-from-scratch
Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.
- Owner
- therealoliver (personal account)
- Stars
- Stars: 630
- Forks
- Forks: 52
- Language
- Jupyter Notebook
- License
- MIT
- Created
- 2025
- Topics
- inferencekv-cachellamallmsattentionattention-mechanismgptlanguage-modelllm-configurationmask
- Tier
- Alpha (250 to 699 ★) What this tier means
Nearby in Jupyter Notebook
All Jupyter Notebook repos- cfgranda/ps4dsStars: 631Jupyter NotebookAlpha
- Glorf/recipenlgStars: 630Jupyter NotebookAlpha
- FrozenBurning/Text2LightStars: 630Jupyter NotebookAlpha
- amygdala/tensorflow-workshopStars: 629Jupyter NotebookAlpha
- drabastomek/learningPySparkStars: 629Jupyter NotebookAlpha