ended7월 25일· 1 sources
ML Without Magic: Building a Tiny Language Model in Pure Node.js and Watching Every Weight Change
Why it matters
Tokenization → embeddings → causal Transformer → LM head → softmax → loss → backpropagation. No TensorFlow, no PyTorch, and no hidden autograd. Repository: tiny-language-model-neuro-js. Most explanati...
1
Sources
+0
24h
—
Growth
6d
Active