search

evidentlyai / evidently

Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
https://www.evidentlyai.com/evidently-oss
Apache License 2.0
5.2k stars 583 forks source link

Support new HF models. #1129

Closed Liraim closed 3 months ago

Liraim commented 4 months ago

Examples:

ColumnSummaryMetric(GeneralHuggingFaceModel(model="SamLowe/roberta-base-go_emotions", params={"label": "disappointment"}).on("Review_Text"))
ColumnSummaryMetric(GeneralHuggingFaceModel(model="openai-community/roberta-base-openai-detector", params={"score_threshold": 0.7}).on("Review_Text"))
ColumnSummaryMetric(GeneralHuggingFaceModel(model="MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli", params={"labels": ["positive", "negative"]}).on("Review_Text"))
ColumnSummaryMetric(GeneralHuggingFaceModel(model="DaNLP/da-electra-hatespeech-detection").on("Review_Text"))
ColumnSummaryMetric(GeneralHuggingFaceModel(model="facebook/roberta-hate-speech-dynabench-r4-target").on("Review_Text"))
ColumnSummaryMetric(HuggingFaceToxicityModel().on("Review_Text"))
ColumnSummaryMetric(HuggingFaceToxicityModel(model="DaNLP/da-electra-hatespeech-detection", toxic_label="offensive").on("Review_Text"))