Update README.md

README.md

@@ -227,7 +227,7 @@ Keep in mind that base model is not fine-tuned for downstream tasks out-of-the-b
 
 # Training Data
 - Total Training Tokens: ~4.2 trillion tokens
-- Corpus: StackV1, Starcoderdata, StackV2, CommitPack, English wiki
+- Corpus: The Stack, StarCoder Training Dataset, The Stack v2, CommitPack, English Wikipedia
 
 # Training Details
 - Context Window: 8,192 tokens
@@ -346,8 +346,7 @@ if __name__ == "__main__":
     print(fibonacci(10))
 """
 
-encoded_input = tokenizer(f"<fim_suffix>suffix<fim_prefix>{prefix}<fim_middle>", return_tensors='pt', return_token_type_ids=False)
-input_len = len(encoded_input["input_ids"][0])
+encoded_input = tokenizer(f"<fim_suffix>{suffix}<fim_prefix>{prefix}<fim_middle>", return_tensors='pt', return_token_type_ids=False)
 out = model.generate(
     **encoded_input,
     max_new_tokens=100,