This generator is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.
evo-design/proto-language/proto_language/generator/position_weight_generator.pyGenerator contributors
dguo8412
Convert logit distributions into discrete proposal sequences.
Reads dguo8412seq.logits from each proposal sequence, applies softmax, and
writes the decoded string back to seq.sequence. Supports deterministic
argmax decoding or stochastic categorical sampling.
Designed for gradient-based optimizers that update seq.logits directly
and need discrete sequences for handoff or tracking.
API Reference
Configuration for position-specific sequence sampling.This generator is intended for optimizers that own position-specific
sequence distributions and need to materialize discrete proposal sequences
for the rest of the framework.
enum
default:"argmax"
How to convert position-specific distributions into discrete proposals.Options:
argmax, categoricalnumber
default:"1.0"
Softmax temperature on logits before decoding. Below 1 sharpens; above 1 flattens. Must be > 0.
SequenceLogitBiasConfig
Optional declarative sequence-symbol bias applied before decoding.
number
default:"1.0"
Optional scale factor applied to logits before adding sequence_bias and decoding.
array
Position indices used in the mean per-position peak-probability metric; None averages over all.
Usage
python