MicroGPT::CooperativeModel
Inherits MicroGPT::MathUtils < Reference < Object
Constructors
Instance methods
active_stream_dims
Stream bandwidth masking: only first active_stream_dims carry signal Allows testing narrower streams without resizing matrices
active_stream_dims=(active_stream_dims : Int32)
Stream bandwidth masking: only first active_stream_dims carry signal Allows testing narrower streams without resizing matrices
all_adam_mats
Collect Adam m/v Mats in same order as all_weight_mats Returns [w0_m, w0_v, w1_m, w1_v, ...] — 2 Mats per weight Mat
attach_bigram(table : BigramTable | TrigramTable | CalculatorExpert)
Attach a bigram table as algorithmic expert 0 Call after initialize — replaces counter if present
counter_pos
True counter: learned positional signal injected directly into stream Only seq_len × stream_dim params — no transformer, no logits
detach_bigram
Sourceeffective_stream_width
Sourceexperts
Sourcehas_counter
Sourcen_experts
Sourceparam_count
Sourcerouter_weights_str
Sourcestream_dim
Sourcew_bigram
Sourcew_writes
Source