@calebwritescode: Andrej Karpathy's explaination of Bigram Language Model explained Bigram LMs, though simple, it provides powerful insight into the inner mechanics of how tokens are processed in language models. This is a pre-amble for what's next: GPT, which is the 2nd part of the series The Bigram model here incorporates: Tokenization, Vocabulary, Negative Loss Function, Cross Entropy, Logits, SoftMax, Optimizer, and AdamW These are essential ingredients to understand in order to build our knowledge on how LLMs really work as we build our case towards attention and GPT #karpathy #deeplearning #bigram #bigramlm #languagemodel #llm #machinelearning #research #agi #largelanguagemodels #compute #explained #hardware

calebwritescode

Open In TikTok:

Region: US

Thursday 18 June 2026 16:54:39 GMT

22524

1368

Music

Download

No Watermark .mp4 (14.06MB) No Watermark(HD) .mp4 (9.93MB) Watermark .mp4 (13.15MB) Music .mp3

Comments

sammymans :

🔥🔥🔥such a good explanation

2026-06-18 17:00:11

Julian Nthoyiwa :

Bro make a YouTube channel you could rival organic chemistry I swear the way you explain it all you could train the next generation of data scientists

2026-06-19 06:03:03

call me cosmic :

It’s so useful, ty for the content

2026-06-18 18:17:55

Seif Hussein :

love this

2026-06-18 17:30:25

Telo :

wassup Caleb

2026-06-18 17:31:25

geez :

Gang remind me to continue this when I wake up I’m at 4:45

2026-06-18 21:43:47

To see more videos from user @calebwritescode, please go to the Tikwm homepage.