---
language:
- en
license: apache-2.0
tags:
- dnotitia
- nlp
- llm
- conversation
- chat
- reasoning
base_model:
- Qwen/Qwen3-14B
library_name: transformers
pipeline_tag: text-generation
---

# Smoothie Qwen

<img src="https://github.com/dnotitia/smoothie-qwen/raw/main/asset/smoothie-qwen-logo.png" width="400" style="max-width: 100%;">

**Smoothie Qwen** is a lightweight adjustment tool that smooths token probabilities in Qwen and similar models, enhancing balanced multilingual generation capabilities. For more details, please refer to <https://github.com/dnotitia/smoothie-qwen>.

## Configuration
- Base model: Qwen/Qwen3-14B
- Minimum scale factor: 0.5
- Smoothness: 10.0
- Sample size: 1000
- Window size: 4
- N-gram weights: [0.5, 0.3, 0.2]

## Unicode Ranges
- Range 1: 0x4e00 - 0x9fff
- Range 2: 0x3400 - 0x4dbf
- Range 3: 0x20000 - 0x2a6df
- Range 4: 0xf900 - 0xfaff
- Range 5: 0x2e80 - 0x2eff
- Range 6: 0x2f00 - 0x2fdf
- Range 7: 0x2ff0 - 0x2fff
- Range 8: 0x3000 - 0x303f
- Range 9: 0x31c0 - 0x31ef
- Range 10: 0x3200 - 0x32ff
- Range 11: 0x3300 - 0x33ff

## Statistics
- Target tokens: 26,153
- Broken tokens: 1,457
- Modified tokens: 27,564