Update README.md

README.md

@@ -143,10 +143,6 @@ model = AutoModelForVision2Seq.from_pretrained(
     "HuggingFaceM4/idefics2-8b-base",
 ).to(DEVICE)
 
-BAD_WORDS_IDS = processor.tokenizer(["<image>", "<fake_token_around_image>"], add_special_tokens=False).input_ids
-EOS_WORDS_IDS = [processor.tokenizer.eos_token_id]
-
-
 # Create inputs
 prompts = [
   "<image>In this image, we can see the city of New York, and more specifically the Statue of Liberty.<image>In this image,",
@@ -158,7 +154,7 @@ inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
 
 
 # Generate
-generated_ids = model.generate(**inputs, bad_words_ids=BAD_WORDS_IDS, eos_token_id=EOS_WORDS_IDS, max_new_tokens=500)
+generated_ids = model.generate(**inputs, max_new_tokens=500)
 generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
 
 print(generated_texts)
@@ -176,10 +172,6 @@ model = AutoModelForVision2Seq.from_pretrained(
     "HuggingFaceM4/idefics2-8b",
 ).to(DEVICE)
 
-BAD_WORDS_IDS = processor.tokenizer(["<image>", "<fake_token_around_image>"], add_special_tokens=False).input_ids
-EOS_WORDS_IDS = processor.tokenizer("<end_of_utterance>", add_special_tokens=False).input_ids + [processor.tokenizer.eos_token_id]
-
-
 # Create inputs
 messages = [
     {
@@ -209,7 +201,7 @@ inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
 
 
 # Generate
-generated_ids = model.generate(**inputs, bad_words_ids=BAD_WORDS_IDS, eos_token_id=EOS_WORDS_IDS, max_new_tokens=500)
+generated_ids = model.generate(**inputs, max_new_tokens=500)
 generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
 
 print(generated_texts)