cyankiwi
/

ERNIE-4.5-VL-28B-A3B-Thinking-AWQ-8bit

Image-Text-to-Text

ernie4_5_moe_vl

feature-extraction

compressed-tensors

Model card Files Files and versions

cpatonn commited on 14 days ago

Commit

0fb6c6c

·

verified ·

1 Parent(s): 2a3c563

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ base_model: baidu/ERNIE-4.5-VL-28B-A3B-Thinking
 ### Quantization Details
-- **Quantization Method:** AWQ
 - **Bits:** 8
 - **Group Size:** 32
 - **Calibration Dataset:** [5CD-AI/LLaVA-CoT-o1-Instruct](https://huggingface.co/datasets/5CD-AI/LLaVA-CoT-o1-Instruct)

 ### Quantization Details
+- **Quantization Method:** cyankiwi AWQ v1.0
 - **Bits:** 8
 - **Group Size:** 32
 - **Calibration Dataset:** [5CD-AI/LLaVA-CoT-o1-Instruct](https://huggingface.co/datasets/5CD-AI/LLaVA-CoT-o1-Instruct)