lunahr/CeluneNorm-0.6B-v1.1
TEXT GENERATIONConcurrency Cost:1Model Size:0.8BQuant:BF16Ctx Length:32kPublished:Apr 3, 2026License:mitArchitecture:Transformer Open Weights Cold

CeluneNorm-0.6B-v1.1 by lunahr is a 0.8 billion parameter causal language model based on Qwen3-0.6B-Base, specifically designed for lightweight text normalization. It converts poorly formatted input into clean, readable text for TTS and general preprocessing pipelines, preserving original meaning and domain-specific tokens. The model is deterministic and excels at maintaining structure and intent across mixed text inputs with a 32768 token context length.

Loading preview...