openflukeTHE OPEN NOTEBOOK
A book for the curious.
70 chapters inside the Welvet AI engine. Start with why it exists, then follow the ideas into layers, learning, and the systems that connect them.
New to the work? Start with Welvet in plain language, then read What Welvet is. Code examples and reported results below are preserved from the source edition. Read the complete book on one page →
5 entries · Clear filters
VI · Model IO
model/entity — .entity files
HF safetensors are awkward for native topology + packed weights. ENTITY is the Welvet checkpoint.
Read moreVI · Model IO
model/hf — snapshots
Import starts with probing HF/MLX layouts before packing ENTITY.
Read moreVI · Model IO
model/tokenizer
Generate needs encode/decode of HF tokenizer.json without pulling Python.
Read moreVI · Model IO
model/sampling
Logits → token ID needs ArgMax, TopK+temperature, penalties, and chat hygiene in one place.
Read moreVI · Model IO
model/transformer — generate
ENTITY packs must run as Llama-style decoders with KV cache, profiles (SIMD/WebGPU/fused), and chat templates.
Read more