Update README.md

README.md

@@ -47,16 +47,13 @@ model_name = "littleworth/protgpt2-distilled-tiny"
 tokenizer = GPT2Tokenizer.from_pretrained(model_name)
 model = GPT2LMHeadModel.from_pretrained(model_name)
 
-# Ensure tokenizer is padding from the left
-tokenizer.padding_side = "left"
-
 # Initialize the pipeline
 text_generator = TextGenerationPipeline(
     model=model, tokenizer=tokenizer, device=0
 )  # specify device if needed
 
 # Generate sequences
-sequences = text_generator(
+generated_sequences = text_generator(
     "<|endoftext|>",
     max_length=100,
     do_sample=True,
@@ -68,15 +65,20 @@ sequences = text_generator(
     truncation=True,
 )
 
-for i, seq in enumerate(sequences):
-    seq["generated_text"] = seq["generated_text"].replace("<|endoftext|>", "")
-
+def clean_sequence(text):
+    # Remove the "<|endoftext|>" token
+    text = text.replace("<|endoftext|>", "")
+    
     # Remove newline characters and non-alphabetical characters
-    seq["generated_text"] = "".join(
-        char for char in seq["generated_text"] if char.isalpha()
-    )
+    text = "".join(char for char in text if char.isalpha())
+    
+    return text
+
+# Print the generated sequences
+for i, seq in enumerate(generated_sequences):
+    cleaned_text = clean_sequence(seq["generated_text"])
     print(f">Seq_{i}")
-    print(seq["generated_text"])
+    print(cleaned_text)
 ```
 
 ### Use Cases