Smoothie-qwen applied version of ByteDance-Seed/Seed-OSS-36B-Instruct

Tools used

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.

Generation command-line

auto-round --model seed-oss --scheme "W4A16" --format "auto_gptq" --output_dir "./seed-oss-gptq"
Downloads last month
7
Safetensors
Model size
2B params
Tensor type
BF16
·
I32
·
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for hell0ks/Smoothie-Seed-OSS-36B-Instruct-AutoRound-GPTQ-4bit

Quantized
(42)
this model

Dataset used to train hell0ks/Smoothie-Seed-OSS-36B-Instruct-AutoRound-GPTQ-4bit