Text model

Nanbeige4.2-3B

Nanbeige4.2-3B is a compact 3B-parameter agentic language model using a Looped Transformer architecture that reuses transformer layers to boost capacity without adding parameters. It combines strong tool-use and coding-agent performance with broad reasoning across math, science, and general agent benchmarks, supporting configurable thinking and tool-calling modes for multi-turn agentic workflows.

Type
Text
Weights
Open
Downloads
2k
Likes
791
Pipeline
text generation
License
apache-2.0

Model hub

Nanbeige/Nanbeige4.2-3B

Repo
Nanbeige/Nanbeige4.2-3B
Library
transformers
Access
Public
Technical tags and languages
en zh transformers safetensors nanbeige text-generation llm conversational custom_code base_model:Nanbeige/Nanbeige4.2-3B-Base base_model:finetune:Nanbeige/Nanbeige4.2-3B-Base eval-results
Open on Hugging Face

Papers

1

More from Nanbeige LLM Lab

4

About Nanbeige LLM Lab

Nanbeige (Chinese: 南北阁, which means "South and North Pavilion") is a large language model (LLM) research team from BOSS Zhipin.