Model techniques map
Techniquesmodel architecturecontext capacity

specific method · filed under model architecture

N-gram embedding lookup

Short n-grams from the local context index embedding tables whose retrieved vectors augment token representations, adding model capacity with little extra computation.

Also called Local-context N-gram embedding lookup, N-gram Embedding, N-gram embedding lookup memory, N-gram embedding memory, N-gram embeddings, n-gram table.

sources
6
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 6

Documented in

Evidence

6 spans quoted from the sources, strongest treatment first.

Lookups are performed using the local context formed by "the current token plus several preceding tokens", providing additional representations for common phrases and local patterns

coreunclearin Qwen3.8-Flash-NextQwen

Twenty million bigram and trigram embeddings are applied at layer 2, contributing 51B parameters — more than 40% of the checkpoint's non-MTP weight — while adding a table lookup rather than a matrix multiply.

coremodel architecturein Qwen3.8-Flash-NextQwen

short n-grams ending at each token serve as keys into embedding tables, and the retrieved vectors augment the corresponding token representation.

coremodel architecturein Qwen3.8-NextQwen

a 51B lookup memory adds capacity with little per-token compute

coremodel architecturein Qwen3.8-Flash-NextQwen

By indexing with short n-grams, this approach makes parameter scaling highly efficient for memory-constrained accelerators without sacrificing quality.

coreunclearin Qwen3.8-Flash-NextQwen

N-gram Embedding looks up a table using the local context to scale model capacity with very little extra computation

coremodel architecturein Qwen3.8-Flash-NextQwen

Filed alongside

Other methods under model architecture :: context capacity.