khhuang
/

chart-to-table

Image-Text-to-Text

vision-encoder-decoder

Inference Endpoints

Model card Files Files and versions Community

khuangaf commited on Dec 27, 2023

Commit

039dd31

·

1 Parent(s): 4eed8c5

update readme

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -39,8 +39,8 @@ decoder_input_ids = processor.tokenizer(input_prompt, add_special_tokens=False,
 outputs = model.generate(
-        pixel_values.to(device),
-        decoder_input_ids=decoder_input_ids.to(device),
         max_length=model.decoder.config.max_position_embeddings,
         early_stopping=True,
         pad_token_id=processor.tokenizer.pad_token_id,

 outputs = model.generate(
+        pixel_values.cuda(),
+        decoder_input_ids=decoder_input_ids.cuda(),
         max_length=model.decoder.config.max_position_embeddings,
         early_stopping=True,
         pad_token_id=processor.tokenizer.pad_token_id,