Efficient Inference With Configurable Beam Search Decoding

via “beam search decoding with configurable generation parameters”

image-to-text model by undefined. 14,17,263 downloads.

Unique: Integrates with HuggingFace's GenerationConfig API, allowing users to save/load generation hyperparameters alongside model weights, ensuring reproducibility and consistency across deployments. Supports both deterministic (beam search) and stochastic (sampling) decoding in the same API.

vs others: More flexible than fixed greedy decoding; beam search quality is comparable to larger models while maintaining the efficiency of the 350M-parameter architecture.