Types & classes — github.com/amazon-science/AnoLLM-large-language-models-for-tabular-anomaly-detection

CodeHub MCPcopy Create free account

hub / github.com/amazon-science/AnoLLM-large-language-models-for-tabular-anomaly-detection / types & classes

Types & classes13 in github.com/amazon-science/AnoLLM-large-language-models-for-tabular-anomaly-detection

⨍ Functions 88 ◇ Types & classes 13

↓ 3 callersClassAnoLLMDataCollator

Overwrites the DataCollatorWithPadding to also pad the labels and not only the input_ids

anollm/anollm_dataset.py:201

↓ 3 callersClassICL

src/baselines/icl.py:130

↓ 2 callersClassAnoLLM

AnoLLM Class The AnoLLM class handles the whole generation flow. It is used to fine-tune a large language model for tabular data, and to sample syn

anollm/anollm.py:27

↓ 2 callersClassDatasetBuilder

src/baselines/icl.py:80

↓ 1 callersClassAnoLLMTrainer

Overwrites the get_train_dataloader methode of the HuggingFace Trainer to not remove the "unused" columns - they are needed later!

anollm/anollm_trainer.py:21

↓ 1 callersClassDTECategorical

src/baselines/dte.py:162

↓ 1 callersClassMLP

src/baselines/dte.py:17

↓ 1 callersClassencoder_a

src/baselines/icl.py:93

ClassAnoLLMDataLoader

Add set_epoch function so that huggingface trainer can call it

anollm/anollm_dataset.py:218

ClassAnoLLMDataset

AnoLLM Dataset The AnoLLM overwrites the _getitem function of the HuggingFace Dataset Class to include the permutation step. Attributes: tokeniz

anollm/anollm_dataset.py:13

src/baselines/dte.py:56

ClassDTEGaussian

src/baselines/dte.py:223

ClassDTEInverseGamma

src/baselines/dte.py:186