toughcent
/

Qwen3-VL-8B-Thinking-bnb-8bit

Image-Text-to-Text

8-bit precision

Model card Files Files and versions

toughcent commited on 22 days ago

Commit

8fc8ea4

·

verified ·

1 Parent(s): 101779a

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -17,6 +17,8 @@ model = Qwen3VLForConditionalGeneration.from_pretrained(
     device_map="auto",
 )
 processor = AutoProcessor.from_pretrained("Qwen3-8B-VL-bnb-8bit")
 messages = [

     device_map="auto",
 )
+# Qwen3VLForConditionalGeneration isn't available on transformers<4.57 but AutoModelForImageTextToText works just fine on lower versions of transformers
 processor = AutoProcessor.from_pretrained("Qwen3-8B-VL-bnb-8bit")
 messages = [