Termsslug: nucleus-sampling

Nucleus Sampling

核采样

Random sampling from a candidate set whose cumulative probability exceeds a threshold

Curated Intelligence

4 items · Page 1/1
Hacker News AIT2·Open Source
62 pts
MAPLE Pruning Runs Gemma 4 26B at 45 TPS on a 6GB GPU

An independent researcher released MAPLE, a structural pruning method for mixture-of-experts LLMs that removes dormant experts, shrinking Gemma 4 26B-A4B from 9.92 GB to 4.75 GB (about 1.48 bits per parameter) so it runs entirely in 6 GB of laptop VRAM at 45.4 tokens per second. The checkpoint is specialized for Python coding and STEM reasoning, and the pipeline is claimed to be domain-agnostic.

Rohan Paul (@rohanpaul_ai)T2·Models
78 pts
DeepMind Study: LLMs Fail to Generate True Randomness Autonomously

A new Google DeepMind paper reveals that LLMs cannot generate true random choices autonomously. Experiments show models favor specific numbers regardless of temperature or sampling settings, but larger models succeed when provided with external random seeds. This finding has direct engineering implications for agent security and decision-making mechanisms relying on randomness.

Hugging Face BlogT1·Tools
68 pts
NVIDIA Releases LogitsProcessorZoo for Fine-Grained LLM Control

NVIDIA released the open-source library LogitsProcessorZoo, enabling developers to directly intervene in language model probability distributions to customize generation behavior. Deeply integrated with Hugging Face Transformers, it offers finer control than traditional decoding strategies, suitable for scenarios requiring strict output constraints.