Smoothie-qwen applied version of Qwen/Qwen3-Next-80B-A3B-Instruct

Using dnotitia/smoothie-qwen version: git+c005f0b

What is Smoothie-Qwen?

By analyzing and adjusting token weights particularly those associated with specific Unicode ranges it helps mitigate unintended biases toward certain languages while preserving the model’s core capabilities.

Notes

Keep in mind this is an experimental model

Downloads last month
44
Safetensors
Model size
80B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for hell0ks/Smoothie-Qwen3-Next-80B-A3B-Instruct

Finetuned
(14)
this model