כתבה
MarkTechPost ·
Laguna S 2.1 - מודל קוד אגנטי פתוח
Poolside Releases Laguna S 2.1, an Open-Weight Agentic Coding Model Punching Above Its Weight Class on SWE-Bench Multilingual
חברת Poolside הוציאה את Laguna S 2.1, מודל קוד אגנטי פתוח בעל 118B פרמטרים. המודל הוכשר על נתוני אימון זהים למודל Laguna XS 2.1 ומתמודד נגד מודלים גדולים יותר כמו DeepSeek-V4-Pro-Max, Nemotron 3 Ultra ו-Inkling.
תקציר מקורי באנגליתPoolside has released Laguna S 2.1 , a 118B-parameter open-weight model built for agentic coding. It is a Mixture-of-Experts (MoE) model with 8B activated parameters per token. It supports a context window of up to 1M tokens in both thinking and no-thinking modes. The weights are on Hugging Face under an OpenMDW-1.1 license, and the model is small enough to run on a single NVIDIA DGX Spark . On long-horizon coding benchmarks, Laguna S 2.1 holds its own against models several times its size, including DeepSeek-V4-Pro-Max, NVIDIA’s Nemotron 3 Ultra, and Thinking Machines’ Inkling. Laguna S 2.1 is a scale-up of the Laguna XS family, trained on the same pre-training data as XS 2.1. What is Laguna S 2.1 The model activates roughly 6.8% of its parameters on any given token. All 118B
קרא במקור המקורי
marktechpost.com
פתח כתבה מקורית