Intel
/

llava-gemma-2b

Image-Text-to-Text

Inference Endpoints

Model card Files Files and versions Community

matthewlyleolson commited on Apr 17

Commit

53252a4

•

1 Parent(s): 4b76d8b

fix bug in conversation

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -54,7 +54,7 @@ processor = LlavaGemmaProcessor(
 # Prepare inputs
 # Use gemma chat template
 prompt = processor.tokenizer.apply_chat_template(
-    [{'role': 'user', 'content': "What's the content of the image?<image>"}],
     tokenize=False,
     add_generation_prompt=True
 )

 # Prepare inputs
 # Use gemma chat template
 prompt = processor.tokenizer.apply_chat_template(
+    [{'role': 'user', 'content': "<image>\nWhat's the content of the image?"}],
     tokenize=False,
     add_generation_prompt=True
 )