fontange
PulseAugur coverage of fontange — every cluster mentioning fontange across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
LLM decoding strategies: Greedy, Beam Search, Sampling, Top-K, and Top-P explained
Language models generate text by turning probability distributions into sequences of tokens, with different decoding strategies leading to varied outputs. Greedy decoding selects the most probable token at each step, wh…
-
AI models systematically exclude human-like token choices, study finds
A new research paper, "The Truncation Blind Spot," published on arXiv, reveals that standard decoding strategies used in text generation models systematically exclude human-like token choices. These strategies, includin…
-
New research analyzes MoE model calibration and discontinuities · 4 sources tracked
Two new research papers explore the complexities of Mixture-of-Experts (MoE) models, particularly concerning calibration and discontinuities. The first paper investigates how expert-level calibration impacts MoE perform…
-
LLM Sampling Parameters Explained: Temperature, Top-P, Top-K, and Min-P
This article explains how to effectively tune the sampling parameters used in Large Language Models (LLMs) to achieve desired output characteristics. It details four common parameters: temperature, top-p, top-k, and min…
-
New Qrita Algorithm Boosts LLM Sampling Efficiency
Researchers have developed Qrita, a novel algorithm designed to enhance the efficiency of Top-k and Top-p sampling in large language models. By employing Gaussian-based sigma-truncation and a quaternary pivot search, Qr…
-
New metric reveals LLM sampling filters suppress linguistic diversity
A new metric called the Word Coverage Score (WCS) has been introduced to assess how standard sampling filters in Large Language Models (LLMs) unintentionally reduce linguistic diversity. The WCS quantifies the pruning o…