The definitions of `B, T, C `
- Dominant language
- Python
- Stars
- 24.9k
- Forks
- 3.3k
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/karpathy/minGPT/blob/4050db60409b5bbaaa3302cee1e49847fc145c65/mingpt/model.py#L62
and referred from http://jalammar.github.io/illustrated-gpt2/
I am remain confused about the definitions of `B, T, C = x.size()`.
vocabulary length, batch_size, and tokenizer size, etc?
Thanks.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with mingpt/model.py at line 62 and compare the surrounding code with the linked Illustrated GPT-2 article. Determine what clarification the project should provide for the three dimensions, then document the definitions in the appropriate location and verify that the wording matches how x.size() is used.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100