← all repositories

inseq-team/inseq

An attribution-based interpretability library for sequence generation models including LLMs.

467 stars Python LLMOps · Eval
inseq
Velocity · 7d
+0.3
★ / day
Trend
steady
star history

Inseq is an open-source library providing feature attribution methods to explain sequence generation models. It integrates with Hugging Face Transformers and Captum, offering tools to identify which input tokens most influenced model outputs during generation. The library supports various attribution techniques for analyzing LLM behavior in tasks like translation, summarization, and text generation.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.