HuggingFaceM4
/

Idefics3-8B-Llama3

Image-Text-to-Text

Inference Endpoints

Model card Files Files and versions Community

andito HF staff commited on Aug 12, 2024

Commit

9af05b7

·

verified ·

1 Parent(s): c9ba4e1

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -89,7 +89,7 @@ image3 = load_image("https://cdn.britannica.com/68/170868-050-8DDE8263/Golden-Ga
 processor = AutoProcessor.from_pretrained("HuggingFaceM4/Idefics3-8B-Llama3")
 model = AutoModelForVision2Seq.from_pretrained(
-    "HuggingFaceM4/Idefics3-8B-Llama3",
 ).to(DEVICE)
 # Create inputs

 processor = AutoProcessor.from_pretrained("HuggingFaceM4/Idefics3-8B-Llama3")
 model = AutoModelForVision2Seq.from_pretrained(
+    "HuggingFaceM4/Idefics3-8B-Llama3", torch_dtype=torch.bfloat16
 ).to(DEVICE)
 # Create inputs