Skip to main content

Crate zsfm_tabfm

Crate zsfm_tabfm 

Source

Re-exports§

pub use config::TabFMConfig;
pub use ensemble::orchestrate::EnsembleParams;
pub use infer::InferConfig;
pub use infer::TabFMModel;
pub use infer::TabFMModelBuilder;

Modules§

config
convert
ensemble
infer
TabFM inference engine, with a real batch dimension B (predict_batch) — e.g. one batch item per ensemble member, so ensemble::orchestrate can share the fixed cost of the 24-block ICL stage across all members in one forward pass instead of paying it once per member. The single-table predict() is a thin B=1 wrapper around the same code path; none of the attention/RMSNorm/RoPE math below changed to add batching — only the four “stage” functions (cell_embed, col_embedding_forward, row_interaction_forward, icl_forward) gained a leading B dimension, via reshapes around the same 3D attention calls they always made (masks/weights are shared scalars across the batch — every member has the same row/feature count, train_size, and d; only cell values and cat_mask vary per member).
tensor_map
Maps tabfm/src/pytorch/model.py state_dict keys (from torch.load(pytorch_model.bin), after conversion to safetensors) to canonical GGUF tensor names.