Update README.md

README.md

@@ -94,7 +94,7 @@ inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
 # olmo = olmo.to('cuda')
 response = olmo.generate(input_ids=inputs.to(olmo.device), max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95)
 print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])
->> '<|user|>\nWhat is language modeling?\n<|assistant|>\nLanguage modeling is a type of natural language processing (NLP) task or machine learning task that...'
+>> '<|user|>\nWhat is language modeling?\n<|assistant|>\nLanguage modeling is a type of natural language processing (NLP) task that...'
 ```
 Alternatively, with the pipeline abstraction:
 ```python
@@ -103,7 +103,7 @@ import hf_olmo
 from transformers import pipeline
 olmo_pipe = pipeline("text-generation", model="allenai/OLMo-7B-SFT")
 print(olmo_pipe("What is language modeling?"))
->> '[{'generated_text': 'What is language modeling?\nLanguage modeling is a type of natural language processing (NLP) task...'}]'
+>> '[{'generated_text': 'What is language modeling?\nLanguage modeling is a type of natural language processing (NLP) task that...'}]'
 ```
 
 Or, you can make this slightly faster by quantizing the model, e.g. `AutoModelForCausalLM.from_pretrained("allenai/OLMo-7B-SFT", torch_dtype=torch.float16, load_in_8bit=True)` (requires `bitsandbytes`).