https://github.com/lzyrapx/llm-grandmaster-notes
๐The path to LLM mastery is paved with broken embeddings and resurrected gradients.
https://github.com/lzyrapx/llm-grandmaster-notes
cuda deep-learning llm reinforcement-learning
Last synced: about 1 year ago
JSON representation
๐The path to LLM mastery is paved with broken embeddings and resurrected gradients.
- Host: GitHub
- URL: https://github.com/lzyrapx/llm-grandmaster-notes
- Owner: lzyrapx
- Created: 2025-05-07T19:24:07.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-10T16:39:33.000Z (about 1 year ago)
- Last Synced: 2025-05-13T14:21:28.596Z (about 1 year ago)
- Topics: cuda, deep-learning, llm, reinforcement-learning
- Homepage:
- Size: 1.95 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# LLM-Grandmaster-Notes
๐The path to LLM mastery is paved with broken embeddings and resurrected gradients.
- Attention
- self attention
- online attention
- flash attention 1 2 3
- softmax
- stardard softmax
- safe softmax