update the generation args

README.md

@@ -92,7 +92,10 @@ inputs = processor(prompts, return_tensors="pt").to(device)
 # --single sample mode
 # inputs = processor(prompts[0], return_tensors="pt").to(device)
 
-generated_ids = model.generate(**inputs, max_length=100)
+# Generation args
+bad_words_ids = tokenizer(["<image>", "<fake_token_around_image>"], add_special_tokens=False).input_ids
+
+generated_ids = model.generate(**inputs, bad_words_ids=bad_words_ids, max_length=100)
 generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
 for i, t in enumerate(generated_text):
     print(f"{i}:\n{t}\n")
@@ -132,9 +135,12 @@ prompts = [
 inputs = processor(prompts, add_end_of_utterance_token=False, return_tensors="pt").to(device)
 # --single sample mode
 # inputs = processor(prompts[0], return_tensors="pt").to(device)
+
+# Generation args
 exit_condition = processor.tokenizer("<end_of_utterance>", add_special_tokens=False).input_ids
+bad_words_ids = tokenizer(["<image>", "<fake_token_around_image>"], add_special_tokens=False).input_ids
 
-generated_ids = model.generate(**inputs, eos_token_id=exit_condition, max_length=100)
+generated_ids = model.generate(**inputs, eos_token_id=exit_condition, bad_words_ids=bad_words_ids, max_length=100)
 generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
 for i, t in enumerate(generated_text):
     print(f"{i}:\n{t}\n")