Page 1 - Showing 8 of 8 posts
View all posts by years →
-
GLM-4.6 with SGLangGLM-4.x series models are foundation models designed for intelligent agents.
7 min read - SWE-bench +
SWE-bench is a benchmark for evaluating large language models on real world software issues collected from GitHub.
5 min read -
GPT OSSOpenAI's open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
12 min read -
Qwen3Qwen3 is the latest addition to the Qwen family of large language models.
14 min read -
slimeAn SGLang-native post-training framework for RL scaling.
6 min read -
Open R1A fully open reproduction of DeepSeek-R1.
16 min read -
Agent CourseBuilding effective agents using the smolagents library.
10 min read -
LLM CourseCourse to get into large language models with roadmaps and Colab notebooks.
27 min read