Classic non-generative text classification library. Upstream archived in 2024.

github.comHTMLMITpushed mar 22 20244.8k forksadded sep 20

Lightweight zero-shot structured extraction: you name the entity types at inference time. Often the comparison point in Jev classification benches.

github.comPythonApache-2.0pushed oct 5319 forksadded sep 20

Fastino successor to GLiNER. Schema-conditioned encoder for classification, extraction, and relations in one pass.

github.comPythonApache-2.0pushed oct 9210 forksadded sep 20

68 pretrained logistic-regression classifiers that run and retrain on CPU: banking77 at 94.3%, CLINC-OOS, spam, plus game-state deciders for Doom and poker. The "do you even need a decision model" baseline; pip package with a live playground. MIT.

github.comPythonMITpushed oct 132 forksadded oct 11

Modernized BERT encoder under most fast classifiers, including Laya's English checkpoint. The non-generative baseline Jev's cost and speed usually get measured against.

github.comPythonApache-2.0pushed mar 1148 forksadded sep 21

Trains and serves routers that pick which LLM should handle a query, based on cost and expected quality, rather than answering the question itself.

github.comPythonApache-2.0pushed aug 10 2024445 forksadded sep 20

Embedding-space route layer for LLMs and agents. Chooses a path from utterance similarity without a generative call.

github.comPythonMITpushed sep 29376 forksadded sep 20

Prompt-free few-shot text classification on Sentence Transformers. Strong when labels are fixed at train time.

github.comJupyter NotebookApache-2.0pushed oct 6272 forksadded sep 20