Urabewe
/

Ace-Step-Captioner-4bit

4-bit precision

Model card Files Files and versions

Urabewe commited on 16 days ago

Commit

5b1ac39

·

verified ·

1 Parent(s): f6f3f55

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ This is a quantized (4bit) version of a Qwen 2.5 Omni model that has been finetu
 - **Base Model:** [Qwen 2.5 Omni](https://huggingface.co/Qwen/Qwen2.5-Omni-7B) by Qwen
 - **Audio Finetuning:** [ACE-Step Captioner](https://huggingface.co/ACE-Step/acestep-captioner)
-- **Quantization:** FP8 quantization by [Urabewe](https://huggingface.co/Urabewe)
 ## License

 - **Base Model:** [Qwen 2.5 Omni](https://huggingface.co/Qwen/Qwen2.5-Omni-7B) by Qwen
 - **Audio Finetuning:** [ACE-Step Captioner](https://huggingface.co/ACE-Step/acestep-captioner)
+- **Quantization:** 4bit quantization by [Urabewe](https://huggingface.co/Urabewe)
 ## License