cortex_rust 0.6.0

High-performance LLM inference with 4-bit quantization and Test-Time Training (TTT)
Documentation 
1
2
3
4
5
6
7
8

//! Evaluation utilities for language models.
//!
//! This module provides functions for evaluating language model quality,
//! including perplexity calculation and other metrics.

mod perplexity;

pub use perplexity::{compute_perplexity, PerplexityResult};